© 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. 51024
    Prev
    Next
    INDEX
    Explanations

    airway

    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
    éĨĭ
    -0.09
    vr
    -0.09
    æĬ±
    -0.09
    åĿı
    -0.09
    _operand
    -0.08
    ippy
    -0.08
     IDM
    -0.08
    ä¸IJ
    -0.08
    -gray
    -0.08
    acles
    -0.08
    POSITIVE LOGITS
    åı¶åŃIJ
    0.10
    ç£ĭ
    0.09
    æĿĥ
    0.09
    åijĽ
    0.09
    åij¼åIJ¸éģĵ
    0.09
    åıijéŁ³
    0.09
    å¼ĢæĶ¾å¼ı
    0.09
     Asi
    0.09
    Speech
    0.09
    辫
    0.09
    Activations Density 0.201%

    No Known Activations