© 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. 6681
    Prev
    Next
    INDEX
    Explanations

    cards

    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
     Kidd
    -0.10
    è¿Ļ段
    -0.09
    ä¸Ģ段
    -0.09
    neo
    -0.09
    è¿ľç¦»
    -0.09
     Russo
    -0.09
     Franken
    -0.08
    estr
    -0.08
    ivec
    -0.08
    (hw
    -0.08
    POSITIVE LOGITS
    çīĮ
    0.11
    顶å°ĸ
    0.10
     card
    0.10
    åī¡
    0.10
    åĴ³
    0.09
    èĢĮåĩº
    0.09
    çİ©æ³ķ
    0.09
     cards
    0.09
    æĪijèĥ½
    0.09
     cdr
    0.09
    Activations Density 0.034%

    No Known Activations