© 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. 22720
    Prev
    Next
    INDEX
    Explanations

    no or not

    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
    æĻ®
    -0.11
    ä¸įå¾Ĺå·²
    -0.09
    .nz
    -0.09
    rush
    -0.09
    vocab
    -0.09
    çĮ®
    -0.09
    ä¸įå®Į
    -0.09
    ardu
    -0.09
    _imm
    -0.09
    鸱
    -0.09
    POSITIVE LOGITS
    å¤ļä¹ħ
    0.10
    èĩªæĿ¥
    0.09
    夹
    0.08
    ä¸į妨
    0.08
    èĩªåĬ¨
    0.08
    éĢ¾æľŁ
    0.08
    ä¸Ģæĸ¹éĿ¢
    0.08
    ắng
    0.08
    èĩªè§ī
    0.08
     Saud
    0.08
    Activations Density 0.053%

    No Known Activations