© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    may begin, be, celebrate, go, find

    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
    ä¸Ńæłĩ
    -0.10
    åŁºæķ°
    -0.10
    æľ¬ç½ij
    -0.09
    æ³ķå®Ŀ
    -0.09
    çļĦå¿ĥæĥħ
    -0.09
     Sears
    -0.09
    ãĥŀãĥ¼
    -0.08
    rade
    -0.08
     imm
    -0.08
    çİĭçīĮ
    -0.08
    POSITIVE LOGITS
    æŁ¥çľĭåħ¨æĸĩ
    0.10
    æĶ¶ç´§
    0.10
    èĩªå¦Ĥ
    0.10
    æĺ¯æľĢ好çļĦ
    0.09
    jian
    0.09
    æŁ¬
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    åħĭæľį
    0.08
    _BAND
    0.08
    æĽ´å¥½åľ°
    0.08
    Activations Density 0.049%

    No Known Activations