© 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. 33043
    Prev
    Next
    INDEX
    Explanations

    bald, bare, naked, stripped

    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
    å¤ķéĺ³
    -0.11
    iman
    -0.09
    éļĶçĿĢ
    -0.09
    ä¼łå¥ĩ
    -0.09
    èĭ
    -0.09
    èľ·
    -0.09
     Alive
    -0.08
    ä¸Ģå®ļèĥ½
    -0.08
    åħįç¨İ
    -0.08
    绵
    -0.08
    POSITIVE LOGITS
    裸
    0.23
     bare
    0.20
     naked
    0.19
     Naked
    0.19
    ç§ĥ
    0.16
    bare
    0.16
     Bare
    0.15
     stripped
    0.15
     barren
    0.13
    空
    0.13
    Activations Density 0.252%

    No Known Activations