© 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. 19878
    Prev
    Next
    INDEX
    Explanations

    check out

    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
    åĴĦ
    -0.09
    诡
    -0.09
     everything
    -0.08
    åĶ§
    -0.08
    Typed
    -0.08
    oke
    -0.07
    妹
    -0.07
     Scr
    -0.07
    ä¸ĢåĪĩ
    -0.07
    è§īéĨĴ
    -0.07
    POSITIVE LOGITS
    çľĭä¸Ģä¸ĭ
    0.11
    çľĭçľĭ
    0.11
    äºĨ解ä¸Ģä¸ĭ
    0.10
    æĿ¥æī¾
    0.10
     воÑĤ
    0.10
    osex
    0.09
    çľģéĴ±
    0.09
    seealso
    0.09
     impro
    0.09
    ä¸ĭåij¨
    0.09
    Activations Density 0.052%

    No Known Activations