© 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. 24077
    Prev
    Next
    INDEX
    Explanations

    members joining bands

    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
    Negative Logits
    串
    -0.10
    UPI
    -0.09
    PropertyParams
    -0.09
    çĿ£
    -0.09
    otec
    -0.09
    æĤ
    -0.08
    ucus
    -0.08
    udder
    -0.08
    jspb
    -0.08
    ImageRelation
    -0.08
    POSITIVE LOGITS
    æĪIJåijĺ
    0.15
    éĺŁåijĺ
    0.13
    ãĥ¡ãĥ³ãĥIJãĥ¼
    0.13
     members
    0.12
    åĽ¢åijĺ
    0.12
     member
    0.11
    -member
    0.11
    สมาà¸Ĭ
    0.10
    åĬłçĽŁ
    0.10
    ç»Ħ建
    0.10
    Activations Density 0.113%

    No Known Activations