© 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. 19604
    Prev
    Next
    INDEX
    Explanations

    Blazer, Power, Land, Spring, Genetics

    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
     SimpleName
    -0.11
    serrat
    -0.09
    lations
    -0.08
    onymous
    -0.08
    øre
    -0.08
    AndFeel
    -0.08
    hound
    -0.08
    ä¸ĸçķĮä¸Ĭ
    -0.08
     minded
    -0.08
    ighbors
    -0.08
    POSITIVE LOGITS
    odore
    0.14
    orem
    0.12
    ramid
    0.11
    etheless
    0.11
    ughter
    0.10
    raries
    0.10
    âĦ¢
    0.09
    åIJ»
    0.09
    tlement
    0.09
    ners
    0.09
    Activations Density 0.884%

    No Known Activations