© 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. 23-RESID-POST-AA
    11. 1111
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULO
    -0.07
    /documentation
    -0.07
    จากการ
    -0.07
    已经
    -0.07
    쐬
    -0.07
    🤰
    -0.07
     suppose
    -0.07
     scary
    -0.07
    .inc
    -0.07
     drove
    -0.07
    POSITIVE LOGITS
    麈
    0.07
    Snapshot
    0.07
    _timestamp
    0.07
    頻道
    0.07
     Gain
    0.07
    痴
    0.06
    נשק
    0.06
    حظ
    0.06
    ends
    0.06
    שני
    0.06
    Activations Density 0.000%

    No Known Activations