© 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. 48627
    Prev
    Next
    INDEX
    Explanations

    following content or actions

    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
    å¨ł
    -0.10
    chen
    -0.09
    lake
    -0.08
    ISH
    -0.08
     lit
    -0.08
    ¼
    -0.08
    æľ
    -0.08
    ITOR
    -0.08
    uf
    -0.08
    pie
    -0.08
    POSITIVE LOGITS
    ç£ķ
    0.09
    äºĨä¸Ģåı£
    0.09
    éĵ¼
    0.09
    åĩ¹
    0.09
    elman
    0.09
    çħĬ
    0.09
    hic
    0.09
    asl
    0.08
     Democrat
    0.08
    ä¿ĿçķĻ
    0.08
    Activations Density 0.001%

    No Known Activations