© 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. 11914
    Prev
    Next
    INDEX
    Explanations

    call for participation

    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
    循
    -0.09
    åı¯è§ģ
    -0.08
     Listen
    -0.08
    æŁĦ
    -0.08
     Rehab
    -0.08
    ÑĦи
    -0.08
    è¿ĺå¾Ĺ
    -0.08
    æĶ¾ä¸ĭ
    -0.08
     Grace
    -0.08
    æĿĥçĽĬ
    -0.08
    POSITIVE LOGITS
    æĭĽåĭŁ
    0.18
    å¾ģéĽĨ
    0.15
    å¾ģ
    0.13
    å¾ģæ±Ĥ
    0.13
    æĭĽæĶ¶
    0.12
    å¾µ
    0.12
    æĭĽ
    0.12
    æĭĽåķĨ
    0.12
    éĤĢ请
    0.11
    åĭŁ
    0.11
    Activations Density 0.112%

    No Known Activations