© 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. 27887
    Prev
    Next
    INDEX
    Explanations

    damage or deformation

    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
    éªĬ
    -0.10
    æĬĬæı¡
    -0.10
    éĵº
    -0.10
    æģ¯
    -0.09
    çİij
    -0.09
    æİĮæı¡
    -0.09
    èĹľ
    -0.09
    çļĦä¼ĺåĬ¿
    -0.09
    ä»ĸ认为
    -0.08
    stable
    -0.08
    POSITIVE LOGITS
    acha
    0.11
    æĶ¹åıĺäºĨ
    0.10
    agos
    0.09
     holes
    0.09
    çĸ®
    0.09
     hole
    0.09
    holes
    0.09
    éĨĴ缮
    0.09
    -hole
    0.08
    jeta
    0.08
    Activations Density 0.074%

    No Known Activations