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

    Neuronpedia

    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. 85849
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    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
    距
    -0.07
     transit
    -0.07
     tá
    -0.07
     transient
    -0.07
    /dis
    -0.07
    公里
    -0.07
    取消
    -0.07
    ieves
    -0.07
     hops
    -0.07
    (elm
    -0.07
    POSITIVE LOGITS
    שירה
    0.07
    progressbar
    0.07
     укра
    0.07
    _FATAL
    0.06
    مؤ
    0.06
    .dst
    0.06
    borah
    0.06
    chant
    0.06
     contexto
    0.06
    أهد
    0.06
    Activations Density 0.060%

    No Known Activations