© 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. 57252
    Prev
    Next
    INDEX
    Explanations

    rules, clauses, sections

    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
    educt
    -0.08
    ened
    -0.08
    Mono
    -0.08
    _GENERIC
    -0.08
    管çIJĨç³»ç»Ł
    -0.08
     Lana
    -0.08
    æĮ£
    -0.08
    som
    -0.07
     luk
    -0.07
    )(*
    -0.07
    POSITIVE LOGITS
    æĭĽ
    0.10
    好å¥ĩå¿ĥ
    0.09
    åĨĴçĿĢ
    0.09
    æŶéĻIJ
    0.09
    ä½Ļ家
    0.09
    äºĭ项
    0.09
    é©°æı´
    0.09
    çĻĸ
    0.09
    åIJ¾
    0.09
    èĩ´çĶµ
    0.09
    Activations Density 0.051%

    No Known Activations