© 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. 32101
    Prev
    Next
    INDEX
    Explanations

    Mon followed by various word endings

    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
    fully
    -0.14
    -0.12
    ting
    -0.10
    ged
    -0.09
    outer
    -0.09
    itious
    -0.09
    gerald
    -0.08
    èŁł
    -0.08
    年纪
    -0.08
    gent
    -0.08
    POSITIVE LOGITS
    itored
    0.16
    strate
    0.14
    omial
    0.11
    tréal
    0.11
    大家ä¸Ģèµ·
    0.11
    stration
    0.10
    enegro
    0.10
    astery
    0.10
    Ñĥма
    0.10
    ality
    0.10
    Activations Density 0.080%

    No Known Activations