© 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. 22626
    Prev
    Next
    INDEX
    Explanations

    barely or bare

    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
    ively
    -0.11
    naire
    -0.10
    amen
    -0.10
    /her
    -0.10
    à¹Į
    -0.09
    frey
    -0.09
    ally
    -0.09
    лиÑĤ
    -0.09
    ä¸į大
    -0.09
    å¤§éĽ¨
    -0.09
    POSITIVE LOGITS
    mente
    0.10
    íŀĪ
    0.10
    foot
    0.09
     dozen
    0.09
    headed
    0.09
    éĴ°
    0.09
    ç»Ĩèĩ´
    0.08
    à¹Ĩ
    0.08
    çĭ°
    0.08
    onth
    0.08
    Activations Density 0.009%

    No Known Activations