© 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. 22135
    Prev
    Next
    INDEX
    Explanations

    version control systems and operations

    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
    _EXPR
    -0.10
    çĭ¼
    -0.10
    è¾Ł
    -0.10
    è±Ĩ
    -0.10
    æĹłåĬĽ
    -0.09
    代è¨Ģ
    -0.09
    趸
    -0.09
    客æĪ·æľįåĬ¡
    -0.09
    .links
    -0.09
    ç»ĦåĽ¾
    -0.09
    POSITIVE LOGITS
    uras
    0.10
     diff
    0.10
     SVN
    0.09
    .diff
    0.09
    Changes
    0.09
    康
    0.09
    orum
    0.09
     Lim
    0.09
     Difference
    0.08
    åıĺåĬ¨
    0.08
    Activations Density 0.279%

    No Known Activations