© 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. 33678
    Prev
    Next
    INDEX
    Explanations

    redistribution and use

    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
    åıijå±ķåīįæĻ¯
    -0.09
    å¾Ĺèµ·
    -0.08
    cycl
    -0.08
    å¼Ģä¼ļ
    -0.08
    OT
    -0.08
    å½ĸ
    -0.08
     плаÑģÑĤ
    -0.07
    аÑĢÑĮ
    -0.07
    å¼Ń
    -0.07
    离èģĮ
    -0.07
    POSITIVE LOGITS
    ponsive
    0.10
    æģĭ人
    0.09
    bbing
    0.09
    ongoose
    0.09
    ENDED
    0.09
    odyn
    0.08
    âļĵ
    0.08
    omy
    0.08
    .returnValue
    0.08
    лÑĥÑĪ
    0.08
    Activations Density 0.242%

    No Known Activations