© 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. 37718
    Prev
    Next
    INDEX
    Explanations

    you have

    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
    æ³ł
    -0.08
     Orchard
    -0.08
    æ¼±
    -0.08
    çĭ¸
    -0.08
    æĸĹ
    -0.08
    ä¹Łéļıä¹ĭ
    -0.08
    PS
    -0.07
     CS
    -0.07
    roid
    -0.07
     (
    -0.07
    POSITIVE LOGITS
    .linkedin
    0.10
    .debugLine
    0.10
    _EDEFAULT
    0.09
    à¹Ĥà¸Ľà¸£à¹ģ
    0.09
    BitFields
    0.09
    SupportedContent
    0.09
    EmptyEntries
    0.09
    ythe
    0.09
     addCriterion
    0.09
    CALLTYPE
    0.09
    Activations Density 0.254%

    No Known Activations