© 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. 1606
    Prev
    Next
    INDEX
    Explanations

    Ultimate followed by Liberty or Fighting

    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
    ners
    -0.10
    edImage
    -0.09
    è¡Įä¸ļçļĦ
    -0.09
    éĤ¨
    -0.09
    常æĢģ
    -0.08
    èĶ¼
    -0.08
    ุ
    -0.08
    mar
    -0.08
    ukt
    -0.08
    avan
    -0.08
    POSITIVE LOGITS
    arily
    0.11
    еÑĢÑĮ
    0.09
    aneously
    0.09
    esimal
    0.09
    gether
    0.09
    owing
    0.09
    åĽ½åĬ¡
    0.09
    MENT
    0.09
    lement
    0.09
    å¤ļæķ°
    0.09
    Activations Density 0.019%

    No Known Activations