© 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. 1876
    Prev
    Next
    INDEX
    Explanations

    acceptance or rejection

    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
    交éĻħ
    -0.09
    æĦĪ
    -0.09
    éªĮæĶ¶
    -0.09
    æѧè§Ĩ
    -0.09
    浪漫
    -0.09
     Affero
    -0.08
    ä»ĭ
    -0.08
    åIJĮè¡Į
    -0.08
    è¶Ĭæĺ¯
    -0.08
    èħĨ
    -0.08
    POSITIVE LOGITS
    æģ¨
    0.10
    ISTER
    0.09
    æŶæŶ
    0.09
    PIP
    0.09
    ister
    0.09
    ç»ĻäºĨ
    0.09
    岸
    0.09
    _ATTACHMENT
    0.08
    wort
    0.08
    opr
    0.08
    Activations Density 0.072%

    No Known Activations