© 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. 23236
    Prev
    Next
    INDEX
    Explanations

    axis and surrounding geometry

    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
    FromClass
    -0.11
    sink
    -0.09
    梢
    -0.09
    redits
    -0.09
    ÑĤÑĮ
    -0.08
    带ä¸Ĭ
    -0.08
    esch
    -0.08
    emos
    -0.08
    Ŀå§ĭ
    -0.08
    elper
    -0.08
    POSITIVE LOGITS
    -axis
    0.11
     axis
    0.10
    éĻ²
    0.10
    ä¸Ĭæľī
    0.10
    ymmetric
    0.10
    .axis
    0.09
    ä¸ĬçļĦ
    0.09
     mund
    0.09
    è¿Ļä¸įæĺ¯
    0.09
    è½´
    0.09
    Activations Density 0.046%

    No Known Activations