© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50707
    Prev
    Next
    INDEX
    Explanations

    waive, exempt, ordinarily

    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
    ä¸įå¤ļ
    -0.08
    agal
    -0.08
    .compiler
    -0.08
     secret
    -0.08
    è¿ĩäºĨ
    -0.08
     deja
    -0.08
     окол
    -0.08
    èĤļ
    -0.08
    inja
    -0.08
    ifact
    -0.08
    POSITIVE LOGITS
     usual
    0.12
    追究
    0.11
    çªł
    0.10
    äºĴéĢļ
    0.10
     ordinarily
    0.10
    éĢļ常
    0.09
    éŀĭåŃIJ
    0.09
     تÙħاÙħ
    0.09
    常è§Ħ
    0.09
    累累
    0.09
    Activations Density 0.103%

    No Known Activations