© 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. 58293
    Prev
    Next
    INDEX
    Explanations

    playoff scenarios and outcomes

    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
    çĸ£
    -0.09
    çıŀ
    -0.08
    .Constant
    -0.08
    äºıæįŁ
    -0.08
    _REPLY
    -0.08
    ÑĢÑĥÑĤ
    -0.08
    çŀİ
    -0.08
    _capability
    -0.08
    åĨĻçļĦ
    -0.08
    /code
    -0.08
    POSITIVE LOGITS
    ä¿Ŀä½ı
    0.10
    å¹´åºķåīį
    0.09
     اÙĦÙħؤ
    0.09
    èī²è°ĥ
    0.09
    ·»
    0.09
    轸
    0.08
    对èĩªå·±
    0.08
    ä¸įç¡®å®ļ
    0.08
     overt
    0.08
    ä¸įç¡®å®ļæĢ§
    0.08
    Activations Density 0.072%

    No Known Activations