© 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. 49079
    Prev
    Next
    INDEX
    Explanations

    new products on market

    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
    erate
    -0.09
    ghi
    -0.08
     Fuse
    -0.08
    Thu
    -0.08
    _expression
    -0.08
    çĬ¯
    -0.08
    åIJ¬å®Į
    -0.08
    ÑĤÑĢо
    -0.08
    akis
    -0.08
     conven
    -0.08
    POSITIVE LOGITS
    å¸ĤéĿ¢ä¸Ĭ
    0.12
    å¸Ĥåľºä¸Ĭ
    0.11
    åĬłåĽº
    0.10
    æ±Łæ¹ĸ
    0.10
    èĢĮæĿ¥
    0.09
    çĹķ迹
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    lingen
    0.09
    éĻį临
    0.09
    çłľ
    0.09
    Activations Density 0.075%

    No Known Activations