© 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. 31836
    Prev
    Next
    INDEX
    Explanations

    wireless, mobile, networks

    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
    è·ijäºĨ
    -0.09
     Continent
    -0.09
    æĻ®æ³ķ
    -0.09
    失踪
    -0.09
    æľºæŀĦ
    -0.08
    çł´éŨ
    -0.08
    ri
    -0.08
     Fury
    -0.08
    .pid
    -0.08
    sha
    -0.08
    POSITIVE LOGITS
    ennen
    0.09
    jong
    0.08
     subrange
    0.08
    éĴ±è´¢
    0.08
    .Bind
    0.08
    ä¸įçŁ¥
    0.08
    æįī
    0.08
    åıijå¸ĥçļĦ
    0.08
    _nsec
    0.08
     weblog
    0.08
    Activations Density 0.142%

    No Known Activations