© 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. 51036
    Prev
    Next
    INDEX
    Explanations

    honeymoons, custard, chocolate, chili, butter, sauce, honeycomb

    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
    ignon
    -0.09
     báºŃt
    -0.09
    ëł¹
    -0.08
    íĮIJ
    -0.08
    ä»Ĩ
    -0.08
    oston
    -0.08
    urer
    -0.08
    人士
    -0.08
    ringe
    -0.08
    unker
    -0.08
    POSITIVE LOGITS
    é»ĺå¥ij
    0.09
    æĻŀ
    0.09
    .Decode
    0.09
    çĽį
    0.09
    bread
    0.09
    peri
    0.09
    zier
    0.09
    èļĢ
    0.09
    æ±ģ
    0.08
    èĢģ人家
    0.08
    Activations Density 0.119%

    No Known Activations