© 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. 27147
    Prev
    Next
    INDEX
    Explanations

    xml and html tags

    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
    ught
    -0.11
    å¿Į
    -0.10
    _reads
    -0.10
    eration
    -0.09
    æĴķ
    -0.09
    erator
    -0.09
    å§Ĵ
    -0.09
    GetCurrent
    -0.09
    饰
    -0.09
    读åIJİ
    -0.09
    POSITIVE LOGITS
    éĹ´çļĦ
    0.09
    è£Ļ
    0.09
     Romans
    0.08
    .Phone
    0.08
    åĩłä¹İæīĢæľī
    0.08
    æĸ¹å¼ıè¿Ľè¡Į
    0.08
    åĬłå¿«åıijå±ķ
    0.08
    appable
    0.08
    aces
    0.08
    irt
    0.07
    Activations Density 0.006%

    No Known Activations