© 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. 31108
    Prev
    Next
    INDEX
    Explanations

    public domain or license

    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
    oret
    -0.12
    èħ¥
    -0.10
    人éĢł
    -0.09
    oref
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.09
    åı¯èĥ½åıijçĶŁ
    -0.09
    æĬ±æŃī
    -0.09
    /preferences
    -0.09
    CompleteListener
    -0.09
    ìľ¨
    -0.09
    POSITIVE LOGITS
    (crate
    0.14
    -minded
    0.14
    mente
    0.14
    ity
    0.13
    itaire
    0.13
    ally
    0.13
    ../../../
    0.12
    isé
    0.12
     minded
    0.12
    åĮĸçļĦ
    0.11
    Activations Density 0.095%

    No Known Activations