© 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. 22053
    Prev
    Next
    INDEX
    Explanations

    faculty and staff

    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
    ness
    -0.13
    ened
    -0.09
    sWith
    -0.09
    ingly
    -0.09
     mue
    -0.09
    net
    -0.08
    æĸ°å¸¸æĢģ
    -0.08
    aney
    -0.08
    liness
    -0.08
    ç¼Ĩ
    -0.08
    POSITIVE LOGITS
    uada
    0.09
    urre
    0.09
    ELLOW
    0.09
    ulle
    0.09
    ÑĥлÑĮÑĤ
    0.09
    æµ·æ£ł
    0.09
    ionales
    0.09
    uzzy
    0.09
    Reserved
    0.08
    ãģĵãģĿ
    0.08
    Activations Density 0.010%

    No Known Activations