© 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. 55493
    Prev
    Next
    INDEX
    Explanations

    leading up 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
    oto
    -0.12
    OTO
    -0.10
    ovo
    -0.10
    apan
    -0.09
    isk
    -0.09
    åĿIJçĿĢ
    -0.09
    _ROUT
    -0.08
    åı¦ä¸Ģæĸ¹éĿ¢
    -0.08
    entic
    -0.08
    æīģ
    -0.08
    POSITIVE LOGITS
     cul
    0.12
    ä¸Ģ缴åĪ°
    0.09
    ult
    0.09
    eldo
    0.09
    èĢģ人家
    0.08
    xit
    0.08
    ìĽĥ
    0.08
     мом
    0.08
    illet
    0.08
    æľŁæľ«
    0.08
    Activations Density 0.031%

    No Known Activations