© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 74205
    Prev
    Next
    INDEX
    Explanations

    Phrases that give instructions or direct the reader (second-person imperatives and "you can" style action guidance).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .xmlbeans
    -0.07
    �
    -0.07
     swallow
    -0.07
    傅
    -0.06
     lightweight
    -0.06
     motel
    -0.06
    鳁
    -0.06
     bowl
    -0.06
     düşün
    -0.06
    슛
    -0.06
    POSITIVE LOGITS
     себя
    0.07
    ி�
    0.06
    -processing
    0.06
    (link
    0.06
    IDX
    0.06
     Wort
    0.06
    简约
    0.06
     THEM
    0.06
    为了更好
    0.06
     Perc
    0.06
    Activations Density 2.224%

    No Known Activations