© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37667
    Prev
    Next
    INDEX
    Explanations

    give me you

    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
    åĿ¤
    -0.09
    åľ¨åħ¨çIJĥ
    -0.09
    çŁ¥éģĵèĩªå·±
    -0.08
    åľ¨ä¸ŃåĽ½
    -0.08
    çĤ³
    -0.08
    èĬĥ
    -0.08
    å¨ĺ家
    -0.08
    èħķ
    -0.08
    å©Ĭ
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    POSITIVE LOGITS
    对åħ¶
    0.09
     ÑĤебе
    0.09
    åĽ´
    0.09
     вам
    0.09
     Trav
    0.09
    对åħ¶è¿Ľè¡Į
    0.08
    ä»ĸ
    0.08
     him
    0.08
    ç»Ļä»ĸ
    0.08
    对她
    0.08
    Activations Density 0.082%

    No Known Activations