© 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. 18312
    Prev
    Next
    INDEX
    Explanations

    omission, omit, leave out, missing

    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
    åIJĦ家
    -0.10
    è´²
    -0.08
    æĿľç»Ŀ
    -0.08
    ologie
    -0.08
    çģ¯
    -0.08
     Seen
    -0.08
    å¨ģåIJį
    -0.08
    éģįå¸ĥ
    -0.08
    emb
    -0.08
    飨
    -0.08
    POSITIVE LOGITS
    éģĹæ¼ı
    0.19
    éļIJçŀĴ
    0.13
     omission
    0.13
     missing
    0.13
    缺失
    0.12
    éļIJ
    0.12
    缺
    0.12
    éļ±
    0.12
    missing
    0.12
    èĹıçĿĢ
    0.12
    Activations Density 0.082%

    No Known Activations