© 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. 36007
    Prev
    Next
    INDEX
    Explanations

    kind of, sort of

    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
    جÙĪ
    -0.10
    bud
    -0.09
    isen
    -0.09
    courses
    -0.08
    bug
    -0.08
    两åij¨
    -0.08
    è¯Ħæ¯Ķ
    -0.08
    åĿij
    -0.08
    _RECORD
    -0.08
     Decoration
    -0.08
    POSITIVE LOGITS
     sort
    0.18
     sorts
    0.17
    sort
    0.17
     kind
    0.15
    åı¯ä»¥è¯´æĺ¯
    0.14
    æŁIJç§įç¨ĭ度
    0.14
    æŁIJç§į
    0.13
     sorte
    0.13
    èĪ¬çļĦ
    0.13
     kinda
    0.12
    Activations Density 0.070%

    No Known Activations