© 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. 34048
    Prev
    Next
    INDEX
    Explanations

    profiler sampling instrumentation

    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
    oru
    -0.09
    ewidth
    -0.09
    erts
    -0.09
    çģŃ
    -0.09
    ãģ¾ãĤĭ
    -0.08
    teil
    -0.08
    æī¿è®¤
    -0.08
     automation
    -0.08
    åĪĽå§ĭ
    -0.08
    mpl
    -0.08
    POSITIVE LOGITS
    åŁĭ
    0.11
    èĽĽ
    0.10
    èĢĹ
    0.09
    å¤Ń
    0.09
    éķ¿æŶéĹ´
    0.09
    éļĺ
    0.09
    ç¥Ł
    0.09
    رص
    0.09
    èĥ½éĩı
    0.09
    æĶ¸
    0.09
    Activations Density 0.238%

    No Known Activations