© 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. 20107
    Prev
    Next
    INDEX
    Explanations

    hands or arms

    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
    Net
    -0.09
    atsu
    -0.08
     Net
    -0.08
     rop
    -0.08
    .subtract
    -0.08
    çĥŁèĬ±
    -0.08
    ija
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    è¿Ļæīį
    -0.08
    éĶī
    -0.08
    POSITIVE LOGITS
    亲æīĭ
    0.13
    亲身
    0.12
    åıĮæīĭ
    0.11
    èĤī
    0.11
    亲
    0.10
     hands
    0.10
    亲èĩª
    0.10
     ÑĢÑĥк
    0.10
    äº²çľ¼
    0.10
    缴éĶĢ
    0.09
    Activations Density 0.032%

    No Known Activations