© 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. 30451
    Prev
    Next
    INDEX
    Explanations

    navigate between groups

    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
    åįĩåįİ
    -0.11
     pes
    -0.08
     sponge
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
    åĨ²
    -0.08
    äºĭ
    -0.08
    ippers
    -0.08
    æ¦
    -0.07
    edm
    -0.07
    éĵ°
    -0.07
    POSITIVE LOGITS
    鸦
    0.10
    Mono
    0.09
    grese
    0.08
    éĢ¯
    0.08
    umu
    0.08
    Smarty
    0.08
    汩
    0.08
    çĿ£å¯Ł
    0.08
    ç«ĻçĿĢ
    0.08
    åıªæľīä¸Ģ个
    0.08
    Activations Density 0.073%

    No Known Activations