© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50439
    Prev
    Next
    INDEX
    Explanations

    author of book or film

    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
    оÑĦ
    -0.10
    åĴ¨
    -0.10
    åİŁåĪĽ
    -0.09
    å¢ĥå¤ĸ
    -0.09
    å½ĵå¹´
    -0.09
    踽
    -0.09
    åıįå°Ħ
    -0.08
    åĢ«
    -0.08
    ,retain
    -0.08
    微微
    -0.08
    POSITIVE LOGITS
    人éĻħåħ³ç³»
    0.09
    rÃŃ
    0.09
    åł¤
    0.09
     sez
    0.08
    uly
    0.08
     gef
    0.08
    æ¼Ķ
    0.08
    esian
    0.08
    羣å®ŀçļĦ
    0.08
     arbit
    0.08
    Activations Density 0.069%

    No Known Activations