© 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. 23190
    Prev
    Next
    INDEX
    Explanations

    historical dates and places

    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
    éļıå¤Ħåı¯è§ģ
    -0.10
    å¥Ĺ
    -0.09
    ä»Ĭå¹´
    -0.09
    ór
    -0.08
    çĶľçĶľ
    -0.08
    endregion
    -0.08
    çĿ½
    -0.08
    porte
    -0.08
    port
    -0.08
    pectrum
    -0.08
    POSITIVE LOGITS
    æĹ¶æľŁ
    0.11
    -era
    0.10
    ä¸ī大
    0.08
    è¡ĮæĶ¿åĮº
    0.08
    å®ł
    0.08
    vat
    0.08
    ´Ģ
    0.08
     necessity
    0.08
    å²³
    0.08
    ward
    0.08
    Activations Density 0.150%

    No Known Activations