© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10511
    Prev
    Next
    INDEX
    Explanations

    his work or time

    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
    绥
    -0.08
    eor
    -0.08
    åij½é¢ĺ
    -0.08
    uds
    -0.08
    drs
    -0.08
    earer
    -0.08
    sort
    -0.08
    éļħ
    -0.08
    sm
    -0.08
     optim
    -0.08
    POSITIVE LOGITS
     stint
    0.11
    æ¸Ĺ
    0.10
     efforts
    0.10
    æĬķåħ¥åĪ°
    0.09
     dealings
    0.09
    çĶŁæ´»åľ¨
    0.09
    çļĦæŶéĹ´éĩĮ
    0.09
    浸
    0.09
     дÑĢÑĥз
    0.09
    awa
    0.09
    Activations Density 0.098%

    No Known Activations