© 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. 2454
    Prev
    Next
    INDEX
    Explanations

    co. followed by . or company names

    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
    кÑĢаÑĤ
    -0.11
    оÑģÑĮ
    -0.10
    ãģĦãģ¾ãģĻ
    -0.10
    labs
    -0.10
    naire
    -0.10
    ãĤĤãģĨ
    -0.10
    sson
    -0.09
    ista
    -0.09
    /or
    -0.09
    ment
    -0.09
    POSITIVE LOGITS
    ombo
    0.11
    resh
    0.11
    ording
    0.10
    quette
    0.10
    ä¿©
    0.10
    ÖĤ
    0.10
    ffer
    0.09
    alesce
    0.09
     gái
    0.09
    elho
    0.09
    Activations Density 0.036%

    No Known Activations