© 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. 4433
    Prev
    Next
    INDEX
    Explanations

    BC, LNG, Highway, Wood

    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
    åĬłæĭ¿å¤§
    -0.10
    æĸ°è¥¿åħ°
    -0.10
     Québec
    -0.09
    澳大åĪ©äºļ
    -0.09
    NZ
    -0.09
     Quebec
    -0.09
    澳洲
    -0.09
     Ontario
    -0.09
     Canada
    -0.08
    åįģæĿ¡
    -0.08
    POSITIVE LOGITS
    åĨ¤
    0.11
    éĻ¢åŃIJ
    0.11
    .webkit
    0.10
    åĬ¿
    0.10
    WebKit
    0.10
    西åįĹ
    0.10
    otype
    0.10
    æ¹ĺ西
    0.09
     ACM
    0.09
    omite
    0.09
    Activations Density 0.142%

    No Known Activations