© 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. 1976
    Prev
    Next
    INDEX
    Explanations

    professionals trained

    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
    ogan
    -0.08
    istor
    -0.08
    大èĤ¡ä¸ľ
    -0.08
    æĢľ
    -0.08
    hip
    -0.08
    feit
    -0.08
    佶
    -0.08
    riel
    -0.08
    itu
    -0.07
    jen
    -0.07
    POSITIVE LOGITS
    èµ·æĿ¥äºĨ
    0.12
    еÑģÑĮ
    0.11
    NING
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    gers
    0.10
    çĹĪ
    0.09
    以为
    0.09
    äºĨä¸Ģæī¹
    0.09
    lift
    0.09
    为主
    0.09
    Activations Density 0.020%

    No Known Activations