© 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. 35331
    Prev
    Next
    INDEX
    Explanations

    portion, share, proportional, percentage, distribute

    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
    çĥŃå¿ĥ
    -0.10
    éĶĢ
    -0.09
    _EXTERNAL
    -0.09
    nuts
    -0.08
    å¹Ħ
    -0.08
     rub
    -0.08
    黾
    -0.08
    iera
    -0.08
    å±ł
    -0.08
    orth
    -0.08
    POSITIVE LOGITS
    份é¢Ŀ
    0.13
    è¿Ļéĥ¨åĪĨ
    0.12
    æ¯Ķä¾ĭ
    0.12
    portion
    0.11
    ä¸Ģéĥ¨åĪĨ
    0.11
     share
    0.10
     portion
    0.10
    sharing
    0.10
    éĤ£ä»½
    0.09
    éĥ¨åĪĨ
    0.09
    Activations Density 0.073%

    No Known Activations