© 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. 54831
    Prev
    Next
    INDEX
    Explanations

    library

    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
    /OR
    -0.11
    èħĪ
    -0.09
    imas
    -0.09
    çłĶ究ä¸Ńå¿ĥ
    -0.09
    alus
    -0.08
    nable
    -0.08
    /or
    -0.08
    ted
    -0.08
    imizer
    -0.08
    alink
    -0.08
    POSITIVE LOGITS
    RARY
    0.18
    raries
    0.17
    rarian
    0.16
    -minded
    0.13
    erty
    0.12
    ../../../
    0.10
     minded
    0.09
    ertas
    0.09
    ç»Ļèĩªå·±
    0.09
    ond
    0.08
    Activations Density 0.061%

    No Known Activations