© 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. 61248
    Prev
    Next
    INDEX
    Explanations

    numbers and abbreviations

    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
    á½´
    -0.10
    gettext
    -0.09
    inkle
    -0.09
    ONA
    -0.09
    满满
    -0.09
    elder
    -0.09
    à¸ĵ
    -0.09
    uye
    -0.09
    UCH
    -0.09
    FieldType
    -0.08
    POSITIVE LOGITS
    ä¿İ
    0.09
     пÑĢоÑĦеÑģÑģионалÑĮн
    0.08
    樱èĬ±
    0.08
    äºİæĺ¯æĪij
    0.08
    å®ŀäºĭ
    0.08
    undance
    0.08
    ç¯
    0.08
     Ñģобой
    0.08
     Fry
    0.08
    éªŀ
    0.08
    Activations Density 0.165%

    No Known Activations