© 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. 10729
    Prev
    Next
    INDEX
    Explanations

    interpretation or interpret

    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
    bread
    -0.09
     Hind
    -0.08
    ê¼´
    -0.08
    èijµ
    -0.08
    çŀij
    -0.08
    å¤į
    -0.08
    交代
    -0.08
    stag
    -0.08
     Sy
    -0.08
    brook
    -0.08
    POSITIVE LOGITS
     Interpret
    0.18
     interpretation
    0.17
    interpret
    0.17
    解读
    0.17
     interpretations
    0.17
     interpret
    0.16
     interpreting
    0.14
     interpreted
    0.14
    interpreted
    0.14
     interpre
    0.14
    Activations Density 0.024%

    No Known Activations