© 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. 27852
    Prev
    Next
    INDEX
    Explanations

    growl at

    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
    çľ·
    -0.12
    幡
    -0.11
    ç»ıåİĨ
    -0.10
    æĻķ
    -0.10
    èĻŀ
    -0.10
    éģŃ
    -0.09
    æĢ»ä½ĵè§ĦåĪĴ
    -0.09
    忽
    -0.09
    头çĸ¼
    -0.09
    æ®ģ
    -0.09
    POSITIVE LOGITS
    åIJ¼
    0.13
    åij²
    0.11
    é¾ĩ
    0.11
    åĴ¬
    0.11
    çįł
    0.11
    ica
    0.11
    礼
    0.10
    çīĻ齿
    0.10
    æıĸ
    0.10
    ä¾µçĬ¯
    0.10
    Activations Density 0.035%

    No Known Activations