© 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. 61306
    Prev
    Next
    INDEX
    Explanations

    discount or free offers

    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
    atform
    -0.10
    inton
    -0.10
    HEN
    -0.09
    æĥķ
    -0.09
    inski
    -0.08
    ÑĢож
    -0.08
    istol
    -0.08
    è¾ĸåĮºåĨħ
    -0.08
    gings
    -0.08
    ague
    -0.08
    POSITIVE LOGITS
    ably
    0.10
    æĶ¾æīĭ
    0.10
    enance
    0.09
    ãģªãĤĬ
    0.08
    åĮĿ
    0.08
    oble
    0.08
    /free
    0.08
    ä¸ĭæĿ¥
    0.08
    ary
    0.08
     ìĽ
    0.08
    Activations Density 0.009%

    No Known Activations