© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19342
    Prev
    Next
    INDEX
    Explanations

    emeritus or emergent

    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
    rames
    -0.09
    warts
    -0.09
    èĢIJå¿ĥ
    -0.09
    uran
    -0.09
    rans
    -0.08
    ree
    -0.08
    erman
    -0.08
    ç»ıåİĨ
    -0.08
    eln
    -0.08
     bè
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.12
    èķ¤
    0.11
    oto
    0.10
    åĽłä¸ºæĪij
    0.10
    ³
    0.10
    æĪijä¹Ł
    0.10
    äºĨèĩªå·±çļĦ
    0.10
    èĩªæĿ¥
    0.09
    ãģĹãģı
    0.09
    ãģĹãģĦ
    0.09
    Activations Density 0.005%

    No Known Activations