© 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. 23226
    Prev
    Next
    INDEX
    Explanations

    college sports

    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
     UEFA
    -0.09
    ä¹ıåĬĽ
    -0.09
     mer
    -0.09
    колÑĮ
    -0.08
    ä¹ĭç±»
    -0.08
    leaf
    -0.08
    icas
    -0.08
     пÑĢоиÑģ
    -0.08
    åķĸ
    -0.08
    沤
    -0.08
    POSITIVE LOGITS
    iot
    0.09
    åĬŁè¯¾
    0.09
    _singleton
    0.08
    æľĹ
    0.08
    iph
    0.08
    é²Ī
    0.08
    æ·Ļ
    0.08
    incy
    0.08
    涯
    0.08
     best
    0.08
    Activations Density 0.028%

    No Known Activations