© 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. 30645
    Prev
    Next
    INDEX
    Explanations

    free software

    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
    urm
    -0.11
    adays
    -0.11
    urray
    -0.10
    appa
    -0.10
     Bris
    -0.10
    bsites
    -0.10
    æĮŀ
    -0.10
    -0.10
    artic
    -0.10
    _TYPED
    -0.10
    POSITIVE LOGITS
    çĬ¯
    0.08
    vez
    0.08
    s
    0.08
    广éĺĶ
    0.08
    ãģ©ãģĨ
    0.07
    ording
    0.07
    åħ¨çIJĥåĮĸ
    0.07
    ÑĢÑĭв
    0.07
    ãĥ³
    0.07
    çĦ¶æĺ¯
    0.07
    Activations Density 0.646%

    No Known Activations