© 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. 27401
    Prev
    Next
    INDEX
    Explanations

    server configuration and setup

    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
    _sun
    -0.10
    çĤ¹æ»´
    -0.10
     Ngô
    -0.09
    -append
    -0.09
    _REFERER
    -0.09
    书记
    -0.09
    缴å±ŀ
    -0.09
    ç¥Ŀè´º
    -0.09
     street
    -0.08
    夫
    -0.08
    POSITIVE LOGITS
    ãģ¦ãģĦ
    0.10
    ä¸ľè¥¿
    0.10
    avez
    0.09
    lags
    0.09
    åł°
    0.09
    人æķ°
    0.09
     дол
    0.08
    åıijå±ķ模å¼ı
    0.08
    éŃĤ
    0.08
    空
    0.08
    Activations Density 0.119%

    No Known Activations