© 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. 37870
    Prev
    Next
    INDEX
    Explanations

    omni, omni, omni

    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
    zelf
    -0.09
    èĬĴ
    -0.08
     curt
    -0.08
    ansion
    -0.08
    浦
    -0.08
    è¸ı
    -0.08
    داد
    -0.08
    andidate
    -0.08
    enson
    -0.08
    ookie
    -0.08
    POSITIVE LOGITS
    çŁ¥æĻĵ
    0.11
    иÑĤеÑĤ
    0.10
    estr
    0.10
    -purpose
    0.09
    æĢ§çļĦ
    0.09
    PARSE
    0.09
    æĴ¸
    0.09
    ogen
    0.09
    è¾Ī
    0.09
    ständ
    0.09
    Activations Density 0.012%

    No Known Activations