© 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. 34366
    Prev
    Next
    INDEX
    Explanations

    members of

    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
     reck
    -0.09
    istan
    -0.09
    aub
    -0.08
    emu
    -0.08
    æīĢæľīçļĦ
    -0.08
    ehr
    -0.08
    åİī害
    -0.08
    Stroke
    -0.08
    ä¸Ģ举
    -0.08
    æĭĨ
    -0.08
    POSITIVE LOGITS
    clide
    0.10
    èĭ¦èĭ¦
    0.09
    忾
    0.09
     ÑĤоÑĢ
    0.09
    æµ·åįĹçľģ
    0.08
    éģĩéļ¾
    0.08
    ãģ¾ãģĹãģ¦
    0.08
    éĺ²çº¿
    0.08
    ç¥Ŀè´º
    0.08
    å«Ĥ
    0.08
    Activations Density 0.029%

    No Known Activations