© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5990
    Prev
    Next
    INDEX
    Explanations

    volume

    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
    olle
    -0.10
    宾
    -0.09
    å¥ijæľº
    -0.09
    stell
    -0.09
    /vnd
    -0.09
    ãģ¶ãĤĬ
    -0.08
    çĸĻ
    -0.08
    EAR
    -0.08
    å®ħ
    -0.08
    innen
    -0.08
    POSITIVE LOGITS
    (volume
    0.11
    volume
    0.09
    -volume
    0.09
     volume
    0.09
    ilate
    0.09
    åįģä½³
    0.09
    å¸Ļ
    0.09
    lew
    0.09
    让人们
    0.09
    èµ·æĿ¥
    0.09
    Activations Density 0.025%

    No Known Activations