© 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. 23686
    Prev
    Next
    INDEX
    Explanations

    El Salvador, El Paso, Elastography, Elasectins, Eladrin

    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
    licate
    -0.10
    ably
    -0.09
    è´¿
    -0.09
    åĿļæŀľ
    -0.09
    ÙĦع
    -0.09
    елÑı
    -0.09
    äºļ马
    -0.09
    iculty
    -0.09
    ome
    -0.08
    éĻ¢åŃIJ
    -0.08
    POSITIVE LOGITS
    ../../../
    0.12
    bert
    0.10
    astos
    0.09
    izabeth
    0.09
    ëĿ¼ëıĦ
    0.09
    ucid
    0.09
    /arch
    0.09
    ving
    0.09
    -fashioned
    0.09
    READY
    0.08
    Activations Density 0.056%

    No Known Activations