© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8045
    Prev
    Next
    INDEX
    Explanations

    posthumous or absent

    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
    对å¤ĸ
    -0.09
    vent
    -0.08
    å°ıå¿ĥ
    -0.08
    对æĸ¹
    -0.08
    unga
    -0.08
     public
    -0.08
    è¾£
    -0.08
    ä¸įçĽ¸ä¿¡
    -0.08
    èļģ
    -0.08
    èļĤ
    -0.08
    POSITIVE LOGITS
    缺å¸Ń
    0.19
    è¿ľç¨ĭ
    0.11
    å¾Ĺèµ·
    0.10
    éĢģæĿ¥
    0.10
     absentee
    0.10
    åħį
    0.10
    åĪ°åľº
    0.10
    éģ¥æݧ
    0.10
    书éĿ¢
    0.09
    å§Ķæīĺ
    0.09
    Activations Density 0.069%

    No Known Activations