© 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. 34791
    Prev
    Next
    INDEX
    Explanations

    as possible

    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
    ç´¯
    -0.11
    tems
    -0.09
    missive
    -0.09
    ä»ĺåĩº
    -0.09
    åIJİç»Ń
    -0.09
    æĽ´éĢĤåIJĪ
    -0.09
    implicitly
    -0.09
    æ·Į
    -0.09
    .Direction
    -0.09
    [out
    -0.09
    POSITIVE LOGITS
     possible
    0.17
    å°½åı¯èĥ½
    0.15
    possible
    0.15
     möglich
    0.13
    Possible
    0.13
     posible
    0.13
     possibile
    0.13
     possÃŃvel
    0.12
     Possible
    0.12
     POSS
    0.12
    Activations Density 0.047%

    No Known Activations