© 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. 7-RESID-POST-AA
    11. 76914
    Prev
    Next
    INDEX
    Explanations

    criterium/criteria

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ав
    -0.08
     adul
    -0.08
    ඞ
    -0.07
     mereka
    -0.07
    😿
    -0.07
    爱人
    -0.07
    ↮
    -0.07
     Cardio
    -0.07
    Ỵ
    -0.07
    الأر
    -0.07
    POSITIVE LOGITS
     dropped
    0.08
    密度
    0.07
    置いて
    0.07
    在我看来
    0.07
    印象深刻
    0.07
     Dec
    0.07
     metal
    0.07
    ,long
    0.07
    ink
    0.07
     talk
    0.07
    Activations Density 0.005%

    No Known Activations