© 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. 28010
    Prev
    Next
    INDEX
    Explanations

    Hall of Fame

    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
    åĴĮæľįåĬ¡
    -0.10
    _CONV
    -0.10
    anium
    -0.10
    okane
    -0.10
    olson
    -0.10
    даÑĩи
    -0.10
    髯
    -0.10
    łéĻ¤
    -0.09
    pector
    -0.09
    opers
    -0.09
    POSITIVE LOGITS
    er
    0.09
    _rq
    0.09
    鸳
    0.09
    ến
    0.08
    ipt
    0.08
    çĪ·
    0.08
    igh
    0.08
    ä¸ŃåĽ½ä¼łç»Ł
    0.08
    ner
    0.08
    ers
    0.08
    Activations Density 0.009%

    No Known Activations