© 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. 1009
    Prev
    Next
    INDEX
    Explanations

    promise and specific terms

    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
    ::*
    -0.10
    沿线
    -0.09
    chied
    -0.09
    串èģĶ
    -0.09
    uez
    -0.09
    èµ°è·¯
    -0.08
    è¾ĭ
    -0.08
     ëĪĦ
    -0.08
    åī¥
    -0.08
    ston
    -0.08
    POSITIVE LOGITS
    åıĤè°ĭ
    0.11
    åı£åı·
    0.09
     promise
    0.09
    .promise
    0.09
    èªĵè¨Ģ
    0.09
    羡
    0.08
    ucher
    0.08
    promise
    0.08
    æī¿è¯º
    0.08
    å¿Ŀ
    0.08
    Activations Density 0.016%

    No Known Activations