© 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. 6585
    Prev
    Next
    INDEX
    Explanations

    quote, estimate, pricing, inquiry, wage, offer

    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
    apel
    -0.10
    éĵ¶è¡Įä¸ļ
    -0.09
    æĿ
    -0.09
    ban
    -0.09
    åĪĨéĶĢ
    -0.09
    éĺµ
    -0.08
    _EVENTS
    -0.08
    缼è¡Į
    -0.08
    _EVT
    -0.08
     бан
    -0.08
    POSITIVE LOGITS
    æĬ¥ä»·
    0.21
    è¦ĭç©įãĤĤãĤĬ
    0.13
    ç¼®
    0.12
    询
    0.12
    ä¼°
    0.11
    å®ļä»·
    0.11
    è¦ĭç©į
    0.11
    ç«ŀä»·
    0.11
    estimate
    0.10
     pricing
    0.10
    Activations Density 0.185%

    No Known Activations