© 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. 62409
    Prev
    Next
    INDEX
    Explanations

    re- prefix + action/state

    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
    iores
    -0.10
    eling
    -0.10
    iras
    -0.09
    edException
    -0.09
    觥
    -0.09
    _draft
    -0.09
    manuel
    -0.08
    okies
    -0.08
    asts
    -0.08
    zyst
    -0.08
    POSITIVE LOGITS
    欢è¿İ大家
    0.09
    çİ¥
    0.08
     tap
    0.08
     háºŃu
    0.08
    åľ¨ç½ij绾
    0.08
    äºĽ
    0.07
    çľĭçĶµå½±
    0.07
    å¼Ģåıij
    0.07
    çĽİ
    0.07
    ä¹ĭå¾Į
    0.07
    Activations Density 0.099%

    No Known Activations