© 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. 50254
    Prev
    Next
    INDEX
    Explanations

    ignition, burning, and charring

    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
    éĩįéĩį
    -0.10
    çģĮ
    -0.09
    åħ¨é¢Ŀ
    -0.09
    ä¸Ģ天
    -0.08
    oust
    -0.08
    æ¶Ľ
    -0.08
    æ´Ĺ
    -0.08
    GetObject
    -0.08
    æ²Ļé¾Ļ
    -0.08
    å·´å·´
    -0.08
    POSITIVE LOGITS
    çªģ
    0.10
    åİĿ
    0.10
    èĩªçĦ¶èĢĮ
    0.10
    èıĺ
    0.10
    çĩĥçĥ§
    0.09
    éĶ¥
    0.09
    æīĭåĬ¿
    0.09
    çIJ¬
    0.09
    .notNull
    0.09
    è¿Ľåı£
    0.09
    Activations Density 0.069%

    No Known Activations