© 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. 63515
    Prev
    Next
    INDEX
    Explanations

    value and valuation

    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
    诳
    -0.10
    æ»ĭåij³
    -0.09
    .nodeType
    -0.09
    vang
    -0.09
    atte
    -0.09
    .Raise
    -0.09
    itive
    -0.09
    æ¶ī
    -0.08
    å¹ķåIJİ
    -0.08
    çļĦ积æŀģæĢ§
    -0.08
    POSITIVE LOGITS
    osal
    0.09
    achs
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    Ñģи
    0.08
    uess
    0.08
    rá
    0.08
    osis
    0.08
    eki
    0.08
     enlist
    0.08
    csr
    0.08
    Activations Density 0.024%

    No Known Activations