© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63774
    Prev
    Next
    INDEX
    Explanations

    SYN control bit

    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
    è¶Ĭæĺ¯
    -0.08
    çĻ¾å®¶
    -0.08
    ações
    -0.08
    erland
    -0.08
    uers
    -0.08
    èĦ±
    -0.08
    ucs
    -0.07
    åĭī强
    -0.07
    èĮģ
    -0.07
    -UA
    -0.07
    POSITIVE LOGITS
    çª
    0.09
    åŁ´
    0.09
    æī§
    0.09
    å¥ĩèij©
    0.09
    ä½ıå®ħ
    0.08
    elic
    0.08
    å³°åĢ¼
    0.08
     ÑĤоÑĢгов
    0.08
    (nt
    0.08
     Libraries
    0.08
    Activations Density 0.112%

    No Known Activations