© 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. 39613
    Prev
    Next
    INDEX
    Explanations

    example.com

    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
    s
    -0.11
    éĶĢ
    -0.08
    åı¦ä¸Ģç§į
    -0.08
    ide
    -0.08
    min
    -0.08
    åı¦ä¸Ģ
    -0.08
    磨
    -0.08
    èĢģå¹´
    -0.07
    æ²»å®ī
    -0.07
    ace
    -0.07
    POSITIVE LOGITS
    è´»
    0.10
    esses
    0.10
    eel
    0.10
    ataka
    0.10
    .ut
    0.10
    翦
    0.09
    ä¿ļ
    0.09
    èµ°è¿ĩ
    0.09
    æĬĬèĩªå·±
    0.09
    éĤ¦
    0.09
    Activations Density 0.145%

    No Known Activations