© 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. 1479
    Prev
    Next
    INDEX
    Explanations

    cleaning, laundered, technician

    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
    éĻ¶çĵ·
    -0.10
    ende
    -0.09
    /documentation
    -0.09
    ç³Ł
    -0.09
    chner
    -0.08
     Regents
    -0.08
    éļIJéļIJ
    -0.08
    åĦĭ
    -0.08
    ån
    -0.08
    ?action
    -0.08
    POSITIVE LOGITS
    HLT
    0.09
    oxy
    0.09
    chor
    0.08
     Mahm
    0.08
    osis
    0.08
    ä¸įåħģ许
    0.08
    HR
    0.08
    edio
    0.08
    æıIJä¾ĽæĽ´å¤ļ
    0.08
    å®ī举
    0.08
    Activations Density 0.003%

    No Known Activations