© 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. 20234
    Prev
    Next
    INDEX
    Explanations

    corporal punishment and abuse

    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
    horn
    -0.10
    æ°©
    -0.09
    åħ¨æĹ¥
    -0.09
    å§ĵ
    -0.09
    erna
    -0.09
    eva
    -0.09
    èµį
    -0.09
    æ¯ĽåŃĶ
    -0.09
    建æĪIJåIJİ
    -0.09
    .TryParse
    -0.09
    POSITIVE LOGITS
    éŀŃ
    0.21
    ç¬ŀ
    0.13
    çĿ£å¯¼
    0.10
    åģ¥
    0.10
    æĿĸ
    0.10
    æĥ©æĪĴ
    0.10
    磫
    0.09
    æ£į
    0.09
    æīĵæ³ķ
    0.09
    ç½ļ
    0.09
    Activations Density 0.020%

    No Known Activations