© 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. 11102
    Prev
    Next
    INDEX
    Explanations

    foreign endings like -ier, -iel, -ied

    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
    ção
    -0.10
    nect
    -0.10
    äºĨèĩªå·±çļĦ
    -0.09
    èŁĨ
    -0.09
    idth
    -0.09
    gether
    -0.09
    ively
    -0.08
    izable
    -0.08
    cript
    -0.08
    ’t
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.12
    -scalable
    0.10
    ãĢħ
    0.10
    è·
    0.10
    eload
    0.09
    ãĥ£
    0.09
    coles
    0.09
    hift
    0.09
    رة
    0.09
    stras
    0.09
    Activations Density 0.094%

    No Known Activations