© 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. 55743
    Prev
    Next
    INDEX
    Explanations

    quad prefix

    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
    oner
    -0.10
    ainen
    -0.09
    akit
    -0.08
    ¡
    -0.08
    äºĮ代
    -0.08
    ulers
    -0.08
    imers
    -0.08
    nych
    -0.08
    chez
    -0.08
    _QMARK
    -0.08
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.10
    UnderTest
    0.09
    weg
    0.09
    ák
    0.09
    amar
    0.09
    åIJ¦
    0.09
    illion
    0.09
    åĩ¡æĺ¯
    0.09
    amarin
    0.09
    extras
    0.09
    Activations Density 0.022%

    No Known Activations