© 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. 61911
    Prev
    Next
    INDEX
    Explanations

    large chunks

    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
     кÑĢай
    -0.12
    åı²ä¸ĬæľĢ
    -0.11
    大大å°ıå°ı
    -0.10
    éĩįçĤ¹åħ³æ³¨
    -0.10
    大纲
    -0.10
    大èĩ´
    -0.10
    大åĬĽåıijå±ķ
    -0.10
    åıijå±ķ模å¼ı
    -0.09
     muse
    -0.09
    ç½Ħ
    -0.09
    POSITIVE LOGITS
    (big
    0.13
    /big
    0.11
     chunk
    0.11
    gest
    0.10
    -scale
    0.10
     (>
    0.10
     chunks
    0.10
    oted
    0.10
    -volume
    0.10
    åĿĹ
    0.10
    Activations Density 0.364%

    No Known Activations