© 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. 48272
    Prev
    Next
    INDEX
    Explanations

    came in

    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
    æĴij
    -0.10
    追赶
    -0.10
    åĭģ
    -0.10
    ç«Ļç«ĭ
    -0.10
    æ²Ľ
    -0.10
    åģĮ
    -0.10
    AccessException
    -0.09
    åľŃ
    -0.09
    åħĪéĶĭ
    -0.09
    åį±
    -0.09
    POSITIVE LOGITS
    bay
    0.09
    official
    0.08
    çķª
    0.08
     Fur
    0.08
    ASK
    0.08
    MI
    0.08
    jiang
    0.08
     overhead
    0.07
     --
    0.07
     official
    0.07
    Activations Density 0.035%

    No Known Activations