© 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. 31755
    Prev
    Next
    INDEX
    Explanations

    Boyle, Carroll, county 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
    alic
    -0.09
    imonial
    -0.09
    ivil
    -0.09
    ÑĦин
    -0.08
    onda
    -0.08
    zing
    -0.08
    ftware
    -0.08
    cing
    -0.08
    emi
    -0.08
    alendar
    -0.08
    POSITIVE LOGITS
    SHA
    0.09
    ../../../
    0.09
    å±ĬæŶ
    0.09
    viso
    0.09
    CHA
    0.09
    å±İ
    0.08
    åľ¨ä¸Ĭæµ·
    0.08
    Palette
    0.08
    sWith
    0.08
    clo
    0.08
    Activations Density 0.003%

    No Known Activations