© 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. 56161
    Prev
    Next
    INDEX
    Explanations

    embedded / embed

    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
    fully
    -0.11
    utan
    -0.10
    åĪĨå·¥
    -0.10
    utch
    -0.09
    erna
    -0.09
    coat
    -0.09
    ¾
    -0.09
    iced
    -0.09
    ses
    -0.09
    pwd
    -0.08
    POSITIVE LOGITS
    ding
    0.13
    /embed
    0.11
    å½
    0.10
    ester
    0.10
     Fare
    0.09
    æľīæľŁ
    0.09
    elu
    0.09
    dings
    0.09
    ulance
    0.09
    arf
    0.09
    Activations Density 0.016%

    No Known Activations