© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35505
    Prev
    Next
    INDEX
    Explanations

    chief -chief lookout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ars
    -0.09
     blind
    -0.08
     ÑģебÑı
    -0.08
    ä½İ温
    -0.08
     dicks
    -0.08
    åİ©
    -0.08
    åIJ¸åħ¥
    -0.08
    éŃĦ
    -0.08
    elter
    -0.08
    à¸Ļà¸Ħร
    -0.08
    POSITIVE LOGITS
    èĻij
    0.10
    éħĭ
    0.10
    éķĿ
    0.09
    èIJ½åIJİ
    0.08
    å¤Ķ
    0.08
     lod
    0.08
    -chief
    0.08
     lookout
    0.08
     pow
    0.08
    chief
    0.08
    Activations Density 0.050%

    No Known Activations