© 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. 54164
    Prev
    Next
    INDEX
    Explanations

    up and phrases

    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
    å¾Ĵ
    -0.10
    ä¸ĬåįĪ
    -0.10
    SPATH
    -0.10
    ооÑĢ
    -0.10
    ãģ¶ãĤĬ
    -0.10
    ä¹ĭå¿ĥ
    -0.09
    omic
    -0.09
    ÑĥлÑĮ
    -0.09
    ectomy
    -0.09
    деÑĢ
    -0.09
    POSITIVE LOGITS
    datable
    0.18
    /down
    0.16
    dater
    0.15
    draft
    0.13
    sert
    0.13
    ilon
    0.12
    DATES
    0.12
    lying
    0.12
    turned
    0.11
    dated
    0.11
    Activations Density 0.165%

    No Known Activations