© 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. 53695
    Prev
    Next
    INDEX
    Explanations

    diversified, differentiation, -ification

    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
    itra
    -0.09
    大åħ¨
    -0.08
    ÑģилÑĮ
    -0.08
    é«ĺæĸ°æĬĢæľ¯
    -0.07
    ç«ĭå¿Ĺ
    -0.07
    аÑĤÑĥÑĢ
    -0.07
    gnu
    -0.07
    éĢ¼
    -0.07
    /gpl
    -0.07
    ValuePair
    -0.07
    POSITIVE LOGITS
    ally
    0.12
    éĵĬ
    0.10
    è¨ĢãģĪãģ°
    0.10
    ä¾Ī
    0.10
    icode
    0.10
    åı¯æĥ³èĢĮçŁ¥
    0.09
    liner
    0.09
    alse
    0.09
    adic
    0.09
    adel
    0.09
    Activations Density 0.013%

    No Known Activations