© 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. 62177
    Prev
    Next
    INDEX
    Explanations

    Muhammmed az

    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
    omat
    -0.10
    опеÑĢ
    -0.10
    å¼Ł
    -0.10
    å¤ļäºĨ
    -0.10
    orf
    -0.09
    ç½Ķ
    -0.09
    累累
    -0.09
    çł£
    -0.09
    åĿ©
    -0.08
    ingly
    -0.08
    POSITIVE LOGITS
     Cyril
    0.10
    åĩĢ
    0.09
    æ·ĭ
    0.08
    éĵ§
    0.08
    NECT
    0.08
     Roads
    0.08
    ambique
    0.08
    马路
    0.08
     trình
    0.08
    çīĽ
    0.08
    Activations Density 0.048%

    No Known Activations