© 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. 39319
    Prev
    Next
    INDEX
    Explanations

    number sequences

    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
    è¿ĩæĿ¥
    -0.10
    èĤ´
    -0.10
    fol
    -0.10
    åĭī
    -0.10
    å±ıå¹ķä¸Ĭ
    -0.09
    主èIJ¥
    -0.09
    訾
    -0.09
    人群ä¸Ń
    -0.09
    çŃīè¡Įä¸ļ
    -0.08
    ders
    -0.08
    POSITIVE LOGITS
    éĻĦåĬł
    0.16
    éĻĦå±ŀ
    0.15
    åı¦æľī
    0.14
    åı¦å¤ĸ
    0.13
    é¢Ŀå¤ĸ
    0.12
    åı¦
    0.11
    è¾ħåĬ©
    0.11
     anc
    0.11
    è¿ĺæľīä¸Ģ个
    0.10
    bonus
    0.10
    Activations Density 0.336%

    No Known Activations