© 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. 33886
    Prev
    Next
    INDEX
    Explanations

    body parts and actions

    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
     Raj
    -0.09
    宪
    -0.09
    æ±Ĺæ°´
    -0.09
    yna
    -0.09
     nave
    -0.09
    åĢı
    -0.08
    éĥ½æľīçĿĢ
    -0.08
    æľ¬æĿ¥å°±
    -0.08
    åĨįåĬłä¸Ĭ
    -0.08
    è¿Ľé©»
    -0.08
    POSITIVE LOGITS
    æij¸
    0.08
    è¯ĥ
    0.08
    _extent
    0.08
    ä¸
    0.08
    åħĭæľį
    0.08
    èļĤèļģ
    0.08
    鸵
    0.07
    _EXTERNAL
    0.07
     cue
    0.07
    çĶij
    0.07
    Activations Density 0.060%

    No Known Activations