© 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. 39320
    Prev
    Next
    INDEX
    Explanations

    coach or manager

    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
    hou
    -0.09
    Generation
    -0.09
    _cu
    -0.09
    ÑĩÑĥв
    -0.09
    æĩĤäºĭ
    -0.09
     Deutsch
    -0.08
    å¤įæŁ¥
    -0.08
     generation
    -0.08
    åŦ
    -0.08
    generation
    -0.08
    POSITIVE LOGITS
    å¾ģéĽĨ
    0.11
    éŀŃ
    0.10
    æĿ²
    0.09
     Maher
    0.09
     Bain
    0.09
    çŁŃæľŁ
    0.08
    à¦Ļ
    0.08
    _PB
    0.08
    å¾ģæ±Ĥ
    0.08
    ica
    0.08
    Activations Density 0.035%

    No Known Activations