© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63835
    Prev
    Next
    INDEX
    Explanations

    missing values and formulas

    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
    å¯Ħ
    -0.08
    çŃīåĢĻ
    -0.08
    åıijåĩº
    -0.08
    sov
    -0.08
    targets
    -0.08
    粪
    -0.08
    *scale
    -0.08
    å«ģ
    -0.08
    ÑģÑħ
    -0.08
    çij°
    -0.08
    POSITIVE LOGITS
    干线
    0.09
    éĵī
    0.09
    FieldType
    0.09
    绣ä¸Ģ
    0.09
    ä¸ĩä¸Ģ
    0.08
    ycl
    0.08
    Trim
    0.08
    æł¸å¿ĥæĬĢæľ¯
    0.08
    .isnan
    0.08
    è¿Ļå¥Ĺ
    0.08
    Activations Density 0.228%

    No Known Activations