© 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. 27611
    Prev
    Next
    INDEX
    Explanations

    vis-a-vis, viscount, visaya, visual

    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
    åħ³éĶ®æĺ¯
    -0.12
    /kubernetes
    -0.10
    tle
    -0.10
    ingly
    -0.10
    èľļ
    -0.09
    èIJĦ
    -0.09
    ROID
    -0.09
    erce
    -0.09
    inged
    -0.09
    entai
    -0.09
    POSITIVE LOGITS
    cosity
    0.13
    itors
    0.11
    ually
    0.09
    ãģ£ãģŁãĤī
    0.09
    .vis
    0.09
    (vis
    0.09
    åıĤè§Ĥ
    0.08
    icut
    0.08
    ibilities
    0.08
    æ³Ĭ
    0.08
    Activations Density 0.025%

    No Known Activations