© 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. 49812
    Prev
    Next
    INDEX
    Explanations

    May followed by a date

    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
    管å§Ķä¼ļ
    -0.11
    ÙĪاب
    -0.09
    gether
    -0.09
    åľ¨è¿ĩåİ»
    -0.09
    isti
    -0.09
    FromClass
    -0.08
    лаг
    -0.08
    umpy
    -0.08
    iddle
    -0.08
    swith
    -0.08
    POSITIVE LOGITS
     mắn
    0.19
    -être
    0.16
    ìį¨
    0.12
    itudes
    0.12
    eters
    0.12
    nard
    0.11
    ACHE
    0.11
    hem
    0.11
    ron
    0.10
    ths
    0.10
    Activations Density 0.054%

    No Known Activations