© 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. 84610
    Prev
    Next
    INDEX
    Explanations

    carbon-13

    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
    电子邮件
    -0.07
     easier
    -0.07
     Least
    -0.07
    .py
    -0.07
    .Con
    -0.07
     pools
    -0.07
     Universidad
    -0.06
     Decor
    -0.06
     difficulty
    -0.06
     может
    -0.06
    POSITIVE LOGITS
    стран
    0.07
    OWL
    0.07
    ıyoruz
    0.07
    /model
    0.07
    ℣
    0.07
    밈
    0.07
     занима
    0.07
     Anc
    0.06
    里面的
    0.06
    פנו
    0.06
    Activations Density 0.005%

    No Known Activations