© 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. 54296
    Prev
    Next
    INDEX
    Explanations

    political campaign

    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
    åIJĦ家
    -0.10
    ç°¸
    -0.10
    çŃīå¾ħ
    -0.10
    è¯ķéªĮåĮº
    -0.10
    laus
    -0.10
    æĪĺåľºä¸Ĭ
    -0.10
    æĸ½å·¥åįķä½į
    -0.09
    åıijå±ķæł¼å±Ģ
    -0.09
    åIJĦåĽ½
    -0.09
    好ä¸į好
    -0.09
    POSITIVE LOGITS
     automat
    0.09
    举
    0.08
     sabotage
    0.08
     advance
    0.08
    ä¸ĢæĹ¥
    0.08
     Gib
    0.08
    umba
    0.08
    çĻ»
    0.08
    ->{'
    0.08
     SHALL
    0.08
    Activations Density 0.010%

    No Known Activations