© 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. 31286
    Prev
    Next
    INDEX
    Explanations

    whiskers or bone

    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
    arya
    -0.09
     laps
    -0.09
    hips
    -0.08
    xic
    -0.08
    大家åı¯ä»¥
    -0.08
    çģ¶
    -0.08
    åıĹ
    -0.08
    ocus
    -0.08
    çĶŁæľº
    -0.08
    Zone
    -0.08
    POSITIVE LOGITS
    ãģİ
    0.10
    è¾ķ
    0.10
    海峡
    0.10
    æ¼Ĥ亮
    0.09
    æĬ»
    0.09
    大æ´ĭ
    0.09
    å·´æĭī
    0.09
    ertime
    0.09
    å¨ĺå¨ĺ
    0.09
    å¥Ń
    0.09
    Activations Density 0.002%

    No Known Activations