© 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. 31941
    Prev
    Next
    INDEX
    Explanations

    life

    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
    æ¯ħåĬĽ
    -0.10
    人大
    -0.10
    纵横
    -0.10
    åľ°åĮºçļĦ
    -0.09
    onic
    -0.09
    æĢ§çļĦ
    -0.09
    碧
    -0.08
    .tbl
    -0.08
    çķĮçļĦ
    -0.08
    rov
    -0.08
    POSITIVE LOGITS
    ÑĤай
    0.09
    opp
    0.09
    .getAmount
    0.08
    .Operator
    0.08
    èIJĺ
    0.08
    ipes
    0.08
    ä¸įåĬ¨
    0.08
    åħµé©¬
    0.08
    DDS
    0.08
    دس
    0.08
    Activations Density 0.035%

    No Known Activations