© 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. 11999
    Prev
    Next
    INDEX
    Explanations

    names like Josh, Julia, Joshua

    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
    edly
    -0.11
    ../../../
    -0.10
    /disable
    -0.10
    ness
    -0.10
    OTE
    -0.09
    ivity
    -0.09
    sWith
    -0.09
    楮
    -0.09
    ¹
    -0.09
    èµį
    -0.09
    POSITIVE LOGITS
    æĿĨèıĮ
    0.10
    Performed
    0.08
    èĦ
    0.08
    clare
    0.08
    andre
    0.08
    PerPage
    0.08
    ccion
    0.08
    /testing
    0.08
    åħ³åĪĩ
    0.08
    anke
    0.08
    Activations Density 0.016%

    No Known Activations