© 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. 57144
    Prev
    Next
    INDEX
    Explanations

    song, sketch, pieces, jig

    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
    umont
    -0.10
     má»Ļ
    -0.10
    åıijå±ķ壮大
    -0.10
    stoff
    -0.09
     Thảo
    -0.09
    лÑİб
    -0.09
    åĪ©äºļ
    -0.08
    æŃĮ声
    -0.08
    .Components
    -0.08
    çļĦäºĭ
    -0.08
    POSITIVE LOGITS
    寸
    0.10
    ä¸Ģ段
    0.10
    çݯèĬĤ
    0.10
    å´
    0.09
    好æĦŁ
    0.09
    åĴĮ个人
    0.09
    ä»ĭ
    0.09
    段
    0.09
    åĴĮæľįåĬ¡
    0.08
    ommen
    0.08
    Activations Density 0.027%

    No Known Activations