© 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. 19928
    Prev
    Next
    INDEX
    Explanations

    High School

    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
    æĺ¯ä¸Ģ件
    -0.09
    åľ°å¸¦
    -0.08
    çĽ´è¾¾
    -0.08
    ãģ¨è¨ĢãĤıãĤĮ
    -0.08
    _Label
    -0.08
    rette
    -0.08
    è¿ĺ以为
    -0.08
    CHANT
    -0.08
    .gs
    -0.07
    azz
    -0.07
    POSITIVE LOGITS
    school
    0.10
    æŁĵ
    0.09
    entifier
    0.09
    olg
    0.08
    sns
    0.08
    -school
    0.08
    agan
    0.08
    íķĻêµIJ
    0.08
    HIR
    0.08
    jen
    0.08
    Activations Density 0.011%

    No Known Activations