© 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. 4509
    Prev
    Next
    INDEX
    Explanations

    granting permission/license

    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
    æ¸ļ
    -0.12
    inx
    -0.11
    aways
    -0.10
    éĻħ
    -0.10
    ry
    -0.09
    rim
    -0.09
    _PAYMENT
    -0.09
     Spar
    -0.09
    ÑģÑı
    -0.09
    away
    -0.09
    POSITIVE LOGITS
    nels
    0.10
    说æĺ¯
    0.09
    ariat
    0.09
    åĴĮæĶ¯æĮģ
    0.09
    entially
    0.09
     chá»ĵng
    0.08
    ably
    0.08
    icularly
    0.08
    ìĤ¬íķŃ
    0.08
    amen
    0.08
    Activations Density 0.030%

    No Known Activations