© 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. 48069
    Prev
    Next
    INDEX
    Explanations

    subscribe or subscribed

    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
    _indent
    -0.11
    -indent
    -0.10
    æĸĻ
    -0.09
    .circular
    -0.09
    亲åŃIJ
    -0.08
    oses
    -0.08
     Pep
    -0.08
    亲æĥħ
    -0.08
    è¸ıåħ¥
    -0.08
    对çĿĢ
    -0.08
    POSITIVE LOGITS
    èľĢ
    0.10
    ruc
    0.09
    åıĸ代
    0.09
    æ¼ĵ
    0.09
     subscribed
    0.08
    涩
    0.08
    æľ«
    0.08
    umba
    0.08
    ä¸į平衡
    0.08
     subscribe
    0.08
    Activations Density 0.043%

    No Known Activations