© 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. 32590
    Prev
    Next
    INDEX
    Explanations

    oyster shells

    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
    ison
    -0.09
    sters
    -0.09
    çĦ¦çĤ¹
    -0.09
    GING
    -0.08
    rror
    -0.08
    young
    -0.08
    eton
    -0.08
    ness
    -0.08
    ç¼ĺ
    -0.08
    .amazonaws
    -0.08
    POSITIVE LOGITS
    èĦ¯
    0.09
    鸥
    0.09
    lsa
    0.09
    便æį·
    0.08
    ç¤ģ
    0.08
    åŃļ
    0.08
     güven
    0.08
     shells
    0.08
    brook
    0.08
    è´Ŀ壳
    0.08
    Activations Density 0.002%

    No Known Activations