© 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. 27678
    Prev
    Next
    INDEX
    Explanations

    shoulder and limb anatomy

    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
     eos
    -0.11
    idal
    -0.10
    éĺµå®¹
    -0.10
    èķī
    -0.10
    å±IJ
    -0.10
    èĥļ
    -0.09
    éļıå¤Ħ
    -0.09
    ç»Ī端
    -0.08
    èĤłèĥĥ
    -0.08
    æļ¹
    -0.08
    POSITIVE LOGITS
    èĤ©
    0.12
    èĥĽ
    0.12
     shoulders
    0.10
     Ridley
    0.10
     Shoulder
    0.09
    æĿ
    0.09
     SCT
    0.08
    èĤ©èĨĢ
    0.08
    麻
    0.08
    èĨĬ
    0.08
    Activations Density 0.051%

    No Known Activations