© 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. 26589
    Prev
    Next
    INDEX
    Explanations

    seeing more 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
    çľĭä¸Ĭåİ»
    -0.11
     found
    -0.09
    çľĭä¼¼
    -0.09
    Found
    -0.09
    éĵİ
    -0.08
    çľĭèµ·æĿ¥
    -0.08
    äºĨåįĬ天
    -0.08
    ç¼°
    -0.08
    å£°éŁ³
    -0.08
     Found
    -0.08
    POSITIVE LOGITS
    ä¸Ģçľ¼
    0.18
    å°±æĥ³
    0.12
    å°±çŁ¥éģĵ
    0.11
    æĽĻåħī
    0.11
    身影
    0.11
    éķľåŃIJ
    0.10
    ä¸Ģè¾¹
    0.10
    ä¸ĢéĿ¢
    0.10
    /he
    0.10
    踪
    0.10
    Activations Density 0.272%

    No Known Activations