© 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. 18783
    Prev
    Next
    INDEX
    Explanations

    English language and translations

    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
    èĢģ人家
    -0.10
    æĢ»ç»Ł
    -0.09
    omer
    -0.08
    æĬŁ
    -0.08
    ysize
    -0.08
    .outputs
    -0.08
    åݨå¸Ī
    -0.08
    辩
    -0.08
    agos
    -0.08
    èĨı
    -0.08
    POSITIVE LOGITS
    ç¿»è¯ij
    0.10
    åł¤
    0.09
     english
    0.09
    PathParam
    0.09
     English
    0.09
    -translate
    0.09
    åĩ°
    0.08
    duk
    0.08
     translations
    0.08
    æ¿®
    0.08
    Activations Density 0.275%

    No Known Activations