© 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. 49920
    Prev
    Next
    INDEX
    Explanations

    CDs or CD versions

    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
    æı©
    -0.09
    纸质
    -0.08
    éĢ¢
    -0.08
    ä»»
    -0.08
    å©¢
    -0.08
    chie
    -0.07
    amy
    -0.07
     inject
    -0.07
    otch
    -0.07
    mer
    -0.07
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.14
    ripp
    0.11
    GINE
    0.10
    rip
    0.10
    .percent
    0.09
    æĥ´
    0.09
    ä¸Ģå¥Ĺ
    0.09
    setDefault
    0.09
    ental
    0.09
     игÑĢÑĭ
    0.09
    Activations Density 0.021%

    No Known Activations