© 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. 57649
    Prev
    Next
    INDEX
    Explanations

    placement on surfaces

    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
    áĥ¨
    -0.10
    è£Ĥ
    -0.09
    Ứ
    -0.09
    幡
    -0.09
    isper
    -0.08
    蹶
    -0.08
    leck
    -0.08
    å´İ
    -0.08
    è£Ĥç¼Ŀ
    -0.08
    çŃĶçĸij
    -0.08
    POSITIVE LOGITS
    çİŁ
    0.10
    ter
    0.09
    é¤IJæ¡Į
    0.09
    享
    0.09
    nil
    0.09
    çķĻç»Ļ
    0.09
    çģ«çĥŃ
    0.08
    头顶
    0.08
    gerald
    0.08
    çªĹ
    0.08
    Activations Density 0.039%

    No Known Activations