© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    examples following "include"

    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
    icy
    -0.10
    entin
    -0.10
    åģĮ
    -0.10
    å¹³åı°ä¸Ĭ
    -0.09
    ä¸Ģå¤ľ
    -0.09
    idon
    -0.09
     coorden
    -0.09
    çŁŃæŶéĹ´åĨħ
    -0.09
    itted
    -0.09
    pare
    -0.09
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.27
    ä½Ĩä¸įéĻIJ
    0.16
    äºĨä¸ĢäºĽ
    0.11
     both
    0.11
    ä»Ģä¹Īåij¢
    0.10
    äºĨä¸Ģ个
    0.09
    ä¸Ģ个éĩįè¦ģ
    0.09
    好å¤ļ
    0.09
    /ex
    0.09
    äºĨä¸Ģ
    0.09
    Activations Density 0.175%

    No Known Activations