© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20379
    Prev
    Next
    INDEX
    Explanations

    Leonard Cohen; Leonard Kirk; Leonard Whiting; Hal Leonard Publishing

    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
    ëģĶ
    -0.12
    ë¡ľìĦľ
    -0.10
     ÐĽÐ¸
    -0.09
    imetype
    -0.09
    iola
    -0.09
    å¾Ĺèµ·
    -0.09
    éªĺ
    -0.09
    steen
    -0.09
    .SQL
    -0.09
    ight
    -0.09
    POSITIVE LOGITS
    t
    0.09
    to
    0.09
    ates
    0.08
    tit
    0.08
    ovo
    0.08
    ing
    0.08
    exus
    0.08
     respect
    0.08
    Ñĭва
    0.08
    éĴĿ
    0.08
    Activations Density 0.005%

    No Known Activations