© 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. 3700
    Prev
    Next
    INDEX
    Explanations

    community groups and organizations

    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
    çĤ¬
    -0.10
     Farr
    -0.09
    ä¸İåħ¶ä»ĸ
    -0.09
     panc
    -0.08
    urs
    -0.08
    ernel
    -0.08
    ough
    -0.08
    èĥĻ
    -0.08
    å±¥
    -0.08
    èī°å·¨
    -0.08
    POSITIVE LOGITS
    çĻ¾å§ĵ
    0.11
    æĢ§çļĦ
    0.11
    ä¸ŃæľĢ
    0.11
    .createElement
    0.10
    åķľ
    0.10
    èµ·æĿ¥
    0.10
    _HIDDEN
    0.09
    /community
    0.09
    icz
    0.09
    agged
    0.09
    Activations Density 0.028%

    No Known Activations