© 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. 2614
    Prev
    Next
    INDEX
    Explanations

    body parts touching

    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
    èIJ½åľ¨
    -0.09
    house
    -0.09
    åĶ¤
    -0.09
    è£ħæī®
    -0.09
    åĶ¤éĨĴ
    -0.08
    è¤Ĵ
    -0.08
    (pass
    -0.08
    å¤Ļ
    -0.08
    het
    -0.08
    座
    -0.08
    POSITIVE LOGITS
    æįĤ
    0.16
    éģ®
    0.11
    çĽĸ
    0.11
    æİ©
    0.11
    èĵĭ
    0.10
    è¦Ĩ
    0.10
    èĴĻ
    0.09
    为客æĪ·
    0.09
    亥
    0.09
    çĽ¾
    0.09
    Activations Density 0.025%

    No Known Activations