© 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. 28116
    Prev
    Next
    INDEX
    Explanations

    put out

    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
    łģ
    -0.09
    ä¸ĭæīĭ
    -0.09
    åĽŀ头
    -0.09
    è¿Ļä¹Ł
    -0.09
    èµ·ä¾Ĩ
    -0.09
    ç±³ç²ī
    -0.09
    åĨľå®¶
    -0.09
    åķ¸
    -0.09
    .tk
    -0.09
    羯
    -0.09
    POSITIVE LOGITS
    ter
    0.11
    å¤Ł
    0.10
    tering
    0.10
     Covered
    0.09
    ERS
    0.08
    微信åħ¬ä¼Ĺ
    0.08
    åıįåĵį
    0.08
    èŀį
    0.08
    entious
    0.08
    esting
    0.08
    Activations Density 0.006%

    No Known Activations