© 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. 27881
    Prev
    Next
    INDEX
    Explanations

    commercial applications, operations, banks, asset, works

    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
    thon
    -0.10
    ToObject
    -0.09
    å®Ļ
    -0.08
    cou
    -0.08
    åįĥåı¤
    -0.08
    èĩªä¸»åĪĽæĸ°
    -0.08
    jos
    -0.08
     ode
    -0.08
    ije
    -0.08
    TAB
    -0.08
    POSITIVE LOGITS
    -commercial
    0.13
     Commercial
    0.12
    åķĨçĶ¨
    0.12
    Commercial
    0.12
    commercial
    0.11
     commercial
    0.11
    åķĨä¸ļ
    0.11
    çŀ¿
    0.11
    åķĨä¸ļåĮĸ
    0.11
    anus
    0.10
    Activations Density 0.055%

    No Known Activations