© 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. 31138
    Prev
    Next
    INDEX
    Explanations

    received promotions book review

    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
     Commons
    -0.09
    /commons
    -0.09
    ENO
    -0.09
    åĢĴ
    -0.09
    webkit
    -0.08
     Trib
    -0.08
    iffs
    -0.08
    DataURL
    -0.08
     ÑĤоÑĩно
    -0.08
    ç¨ĭ度
    -0.08
    POSITIVE LOGITS
    Reviewer
    0.12
    æł·åĵģ
    0.12
    ãĥ¬ãĥĵ
    0.11
    éĩĩ访
    0.11
    èµIJ
    0.11
     reviewer
    0.10
    IGNORE
    0.10
     review
    0.10
    è¯Ħæµĭ
    0.10
    Reviewed
    0.10
    Activations Density 0.134%

    No Known Activations