© 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. 35475
    Prev
    Next
    INDEX
    Explanations

    equity interest

    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
    æħ·æħ¨
    -0.09
    aha
    -0.09
    оÑģÑĮ
    -0.09
    ught
    -0.09
    anie
    -0.09
    etas
    -0.08
    ickey
    -0.08
    تÙĬÙĨ
    -0.08
    ured
    -0.08
    -fashioned
    -0.08
    POSITIVE LOGITS
     minded
    0.13
    çĦ¶æĺ¯
    0.11
    holders
    0.10
     Blond
    0.10
    åīįèĢħ
    0.10
    -minded
    0.10
    ãģĤãĤĭ
    0.10
    ระยะ
    0.09
    alem
    0.09
    /close
    0.09
    Activations Density 0.013%

    No Known Activations