© 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. 31586
    Prev
    Next
    INDEX
    Explanations

    ropes and cords

    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
    ult
    -0.10
    ary
    -0.10
    mente
    -0.09
    lu
    -0.09
    ion
    -0.08
    ry
    -0.08
    /New
    -0.08
    our
    -0.08
    袤
    -0.08
     proposé
    -0.08
    POSITIVE LOGITS
     ë¶Ī구íķĺê³ł
    0.12
    stry
    0.11
    sters
    0.11
    lessly
    0.11
    orda
    0.10
    ä¸ĬçļĦ
    0.09
    нÑıÑĤ
    0.09
    STER
    0.09
    ä¸į解
    0.09
    []{"
    0.09
    Activations Density 0.015%

    No Known Activations