© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51678
    Prev
    Next
    INDEX
    Explanations

    victims of

    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
    è®®åijĺ
    -0.10
    ä¸įä¸ĭ
    -0.10
    zell
    -0.10
    åĩºçİ°éĹ®é¢ĺ
    -0.10
    çĹ
    -0.09
    åıĸèĥľ
    -0.09
    ffen
    -0.09
    æĻģ
    -0.09
    èŁĭ
    -0.09
    è¾Ĥ
    -0.09
    POSITIVE LOGITS
    æĥ¨
    0.08
    Interview
    0.08
    åħ¬åĬ¡
    0.08
    çIJĨåıij
    0.08
    æĹłæĥħ
    0.08
     widow
    0.08
    ìn
    0.08
    æľĿ
    0.08
    åºĵéĩĮ
    0.08
    aos
    0.08
    Activations Density 0.011%

    No Known Activations