© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9967
    Prev
    Next
    INDEX
    Explanations

    cyst and proglottids

    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
    Backing
    -0.09
    å¤©åľ°
    -0.09
    à¸Ĭาย
    -0.08
     пÑĢедназнаÑĩен
    -0.08
    apot
    -0.08
    æ¨Ĭ
    -0.08
    轨
    -0.08
    .populate
    -0.08
    éĿ©
    -0.08
    Declared
    -0.08
    POSITIVE LOGITS
     Escape
    0.10
    å¸ĮæľĽèĩªå·±
    0.09
    icer
    0.09
    fusion
    0.09
    ounds
    0.08
    æĺĢ
    0.08
    å¿«æį·
    0.08
    çĽħ
    0.08
     tung
    0.08
    _salt
    0.08
    Activations Density 0.292%

    No Known Activations