© 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. 1350
    Prev
    Next
    INDEX
    Explanations

    future outcomes

    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
    绣
    -0.11
    åľ¨è¿ĩ渡
    -0.11
    .transitions
    -0.09
    åľ°éģĵ
    -0.09
    ç»Ī身
    -0.09
    èµıæŀIJ
    -0.09
    ä¸ŃéĢĶ
    -0.09
    çݰ代åĮĸ
    -0.09
     iParam
    -0.09
    è°Ľ
    -0.09
    POSITIVE LOGITS
    çĤ¹æ»´
    0.10
    SED
    0.09
    EEE
    0.09
    èį¥
    0.09
    miss
    0.08
    bound
    0.08
    Except
    0.08
    紧紧
    0.08
    èĢģå¸ĪçļĦ
    0.08
    精彩çļĦ
    0.08
    Activations Density 0.021%

    No Known Activations