© 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. 55409
    Prev
    Next
    INDEX
    Explanations

    no charge, cost, reason, effect, time, avail

    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
    æħ·
    -0.10
    ROID
    -0.10
     полÑĥÑĩа
    -0.10
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.09
    isor
    -0.09
     возможноÑģÑĤÑĮ
    -0.09
     вÑģÑĤÑĢ
    -0.09
    çīĩ
    -0.09
     wis
    -0.09
    Ñģкоп
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
     overs
    0.09
    ä¸Ģ家人
    0.09
    ä¸Ģç±»
    0.09
    ä¸Ģ家
    0.09
    让æĪij们
    0.09
    ä½łä»¥ä¸º
    0.09
    ä¿Ŀå®ī
    0.08
    è¿ĩé«ĺ
    0.08
    æĭ¢
    0.08
    Activations Density 0.005%

    No Known Activations