© 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. 27267
    Prev
    Next
    INDEX
    Explanations

    network access

    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
    æĿ¥ä¸įåıĬ
    -0.11
    èħ°éĥ¨
    -0.10
    é¾Ľ
    -0.10
    亲è¿ij
    -0.09
    asti
    -0.09
    ngth
    -0.08
    astic
    -0.08
    AST
    -0.08
    _svc
    -0.08
    ä½ı宿
    -0.08
    POSITIVE LOGITS
    hev
    0.10
     дек
    0.09
    人士
    0.09
    sembler
    0.09
    rias
    0.09
    inkel
    0.08
    iert
    0.08
    ä¸Ģ缴åĪ°
    0.08
    persons
    0.08
    endum
    0.08
    Activations Density 0.023%

    No Known Activations