© 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. 35491
    Prev
    Next
    INDEX
    Explanations

    main / menu

    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
    ç»ĦåIJĪ
    -0.09
    iris
    -0.09
    imitive
    -0.09
    chos
    -0.09
    ary
    -0.08
    çŁ¥å·±
    -0.08
    allon
    -0.08
    á»Ļc
    -0.08
    enc
    -0.08
    \/\/
    -0.08
    POSITIVE LOGITS
    /main
    0.14
    enance
    0.12
    (main
    0.12
    eral
    0.11
    stay
    0.11
    AxisSize
    0.11
    ifest
    0.11
    /Main
    0.10
    esto
    0.10
    AxisAlignment
    0.10
    Activations Density 0.115%

    No Known Activations