© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52532
    Prev
    Next
    INDEX
    Explanations

    if i were to

    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
    ç¼Ń
    -0.11
    éķ°
    -0.10
    ettes
    -0.09
    akt
    -0.08
    ango
    -0.08
    rown
    -0.08
    .Scope
    -0.08
     никÑĤо
    -0.08
    éĴ¦
    -0.08
    ANGO
    -0.08
    POSITIVE LOGITS
    /is
    0.11
    åıįä¹ĭ
    0.09
    bout
    0.09
    åŃ½
    0.09
    rame
    0.09
    èĤ
    0.09
    ÑģÑĤÑĮ
    0.08
    lington
    0.08
    /w
    0.08
    sto
    0.08
    Activations Density 0.009%

    No Known Activations