© 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. 9905
    Prev
    Next
    INDEX
    Explanations

    make or making something

    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
    大çĪ·
    -0.09
     ups
    -0.09
    çķĪ
    -0.08
    缼
    -0.08
    ä»Ļ女
    -0.08
    acht
    -0.08
    _launcher
    -0.08
    缼å¼Ģ
    -0.08
    æ¥ł
    -0.08
    elter
    -0.08
    POSITIVE LOGITS
    leine
    0.12
    ([]*
    0.10
     strides
    0.10
     sure
    0.09
    ure
    0.09
     sense
    0.09
    ioned
    0.09
    çļĦè§Ħå®ļ
    0.09
     excuses
    0.09
    Appear
    0.09
    Activations Density 0.543%

    No Known Activations