© 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. 10610
    Prev
    Next
    INDEX
    Explanations

    contingency plans, contingent groups, collateral damage, collateral estoppel

    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
    cape
    -0.10
    enstein
    -0.09
    stein
    -0.09
    nt
    -0.08
    fas
    -0.08
    .Values
    -0.08
    ä¸ĸ家
    -0.08
    讳
    -0.08
     Pandora
    -0.08
    hl
    -0.08
    POSITIVE LOGITS
    اÙħر
    0.10
    æłī
    0.10
    ÙĪظ
    0.10
    eci
    0.10
    ement
    0.09
    osed
    0.09
    errat
    0.09
    endet
    0.09
    nement
    0.09
    ferred
    0.09
    Activations Density 0.002%

    No Known Activations