© 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. 1638
    Prev
    Next
    INDEX
    Explanations

    page number specifier

    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
    oria
    -0.09
    ãĤ¹ãĤ¿ãĥ¼
    -0.08
    gie
    -0.08
    _Util
    -0.08
     swe
    -0.08
    lish
    -0.08
     seasoned
    -0.08
    åŁºå±Ĥ
    -0.08
    apan
    -0.08
    cion
    -0.08
    POSITIVE LOGITS
    ä»İ容
    0.10
    è¹ij
    0.09
    çIJ¢
    0.09
    åĩ¿
    0.09
    åħīåѦ
    0.09
    æĹ©æĹ©
    0.09
    ä½ľèĢħæīĢæľī
    0.09
    éĿ¡
    0.09
    èĭ¦èĭ¦
    0.09
    itt
    0.09
    Activations Density 0.081%

    No Known Activations