© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    fight or battle against

    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
    lake
    -0.08
    غر
    -0.08
    quest
    -0.08
    æľĢåIJİä¸Ģ次
    -0.08
    rob
    -0.08
     Bates
    -0.08
    èģĸ
    -0.08
    éĥ¨éĺŁ
    -0.08
    uste
    -0.08
    æľį
    -0.08
    POSITIVE LOGITS
    ASF
    0.10
    geme
    0.09
    éĥ
    0.09
    åıĤèĢĥèµĦæĸĻ
    0.09
    ç¾½æ¯Ľ
    0.09
     loser
    0.09
    csi
    0.08
    ç¿»å¼Ģ
    0.08
    ä»Ĺ
    0.08
    æ¯ıä¸Ģ天
    0.08
    Activations Density 0.025%

    No Known Activations