© 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. 22670
    Prev
    Next
    INDEX
    Explanations

    case study

    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
    sel
    -0.09
    è°ı
    -0.09
    oid
    -0.08
    pass
    -0.08
    indo
    -0.08
     bailout
    -0.08
    n
    -0.08
    оÑĩ
    -0.08
    åį¿
    -0.08
    most
    -0.08
    POSITIVE LOGITS
    ä¼łçľŁ
    0.09
    tes
    0.09
    سÙĪ
    0.09
    urations
    0.09
    嬰
    0.09
     اÙĦÙħÙĪضÙĪع
    0.08
    ipl
    0.08
    èĭ£
    0.08
    acas
    0.08
    .GO
    0.08
    Activations Density 0.015%

    No Known Activations