© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7853
    Prev
    Next
    INDEX
    Explanations

    free gift offers

    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
    åħ¬çĽĬ
    -0.09
    osal
    -0.09
    ç³Ł
    -0.09
    çĮķ
    -0.08
     destin
    -0.08
    çĮĸ
    -0.08
    èı±
    -0.08
    幸
    -0.08
    ä¿Ĭ
    -0.08
     dest
    -0.08
    POSITIVE LOGITS
    èµłéĢģ
    0.13
    é¢Ŀå¤ĸ
    0.12
     bonus
    0.11
    èµł
    0.11
    è´Ī
    0.11
     tặng
    0.11
     Extras
    0.10
     Bonus
    0.10
    礼çī©
    0.10
     kèm
    0.10
    Activations Density 0.037%

    No Known Activations