© 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. 34689
    Prev
    Next
    INDEX
    Explanations

    stream processing

    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
    çłĶ究éĻ¢
    -0.09
    幸
    -0.09
    ãĤ¿ãĥ«
    -0.08
    ç½²
    -0.08
    ammers
    -0.08
     ~>
    -0.08
    áĥ¨
    -0.08
    доб
    -0.08
    ndern
    -0.08
    _snd
    -0.08
    POSITIVE LOGITS
    æµģ
    0.13
    .Stream
    0.11
    stream
    0.11
    (stream
    0.10
    eren
    0.10
     stream
    0.10
    -stream
    0.10
    (Stream
    0.10
    .Collectors
    0.10
     streams
    0.10
    Activations Density 0.055%

    No Known Activations