© 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. 61503
    Prev
    Next
    INDEX
    Explanations

    critical, fatal, serious

    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
    åıĹçĽĬ
    -0.10
    æľĢ好çļĦ
    -0.10
    åĿ¦
    -0.09
     Dank
    -0.09
    prech
    -0.08
    ãĤĤãģ£ãģ¨
    -0.08
     snatch
    -0.08
    ieves
    -0.08
     Vend
    -0.08
    å°±æĺ¯è¿Ļæł·
    -0.08
    POSITIVE LOGITS
    èĩ´åij½
    0.19
    严éĩį
    0.14
    严éĩįçļĦ
    0.13
    严éĩįå½±åĵį
    0.12
     Serious
    0.12
    åļ´éĩį
    0.11
    足以
    0.11
     serious
    0.11
    轻微
    0.10
     fatal
    0.10
    Activations Density 0.288%

    No Known Activations