© 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. 56774
    Prev
    Next
    INDEX
    Explanations

    limbs or body parts

    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
    æĸ½
    -0.10
    cline
    -0.09
    RSS
    -0.09
    olk
    -0.09
    积èĵĦ
    -0.09
    åħ»æĬ¤
    -0.09
    olest
    -0.09
    çİĦ
    -0.09
    æѦæŀĹ
    -0.08
    åĶı
    -0.08
    POSITIVE LOGITS
    ä»ĭ
    0.10
    éĴĪ
    0.10
    éĺľ
    0.09
    çĹĶ
    0.09
    ä¸įæĿ¥
    0.09
     cro
    0.09
    ä¾Ŀæŧæĺ¯
    0.08
    å¯Įæľī
    0.08
    cookies
    0.08
    ä¸įäºĪ
    0.08
    Activations Density 0.062%

    No Known Activations