© 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. 31467
    Prev
    Next
    INDEX
    Explanations

    incandescent, differentiation, illumination, iridiation

    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
    ester
    -0.10
    erais
    -0.09
    åħ¥ãĤĮ
    -0.09
    edom
    -0.09
    Å»
    -0.08
    anders
    -0.08
    çĶľçĶľ
    -0.08
    ç¼£
    -0.08
    .mag
    -0.08
    å®ī举
    -0.08
    POSITIVE LOGITS
    ting
    0.10
    0.09
    ors
    0.09
    ä¿Ł
    0.09
    èĽ¹
    0.09
    ä¹İ
    0.09
    é³ŀ
    0.09
    DED
    0.09
    æĨİ
    0.08
    交èŀį
    0.08
    Activations Density 0.011%

    No Known Activations