© 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. 58654
    Prev
    Next
    INDEX
    Explanations

    distance, between, safe

    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
    èĢģå®ŀ
    -0.09
    çģŃ
    -0.09
    ç¼İ
    -0.09
    循
    -0.08
    orris
    -0.08
    æ·³
    -0.08
    æµij
    -0.08
    /pdf
    -0.08
    çIJ¢
    -0.08
    isc
    -0.08
    POSITIVE LOGITS
    è·Ŀ离
    0.29
     distance
    0.25
    distance
    0.24
     Distance
    0.24
    çļĦè·Ŀ离
    0.24
    è·ĿéĽ¢
    0.24
    Distance
    0.22
    .distance
    0.22
    _distance
    0.21
    -distance
    0.20
    Activations Density 0.054%

    No Known Activations