© 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. 61852
    Prev
    Next
    INDEX
    Explanations

    browser extension manifest

    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
    æīĢæıIJä¾Ľ
    -0.09
    .mount
    -0.09
    mount
    -0.09
    éĶ¤
    -0.09
     Shaft
    -0.09
    Locator
    -0.08
    æĪijçļĦå¿ĥ
    -0.08
    Sha
    -0.08
    å±ģèĤ¡
    -0.08
    ole
    -0.08
    POSITIVE LOGITS
    åĿŀ
    0.10
    ãĥĸãĥ©
    0.10
     chrome
    0.10
    quam
    0.09
    .Chrome
    0.09
    _launch
    0.09
    .chrome
    0.09
    åŁĴ
    0.09
    -launch
    0.09
    pmat
    0.09
    Activations Density 0.210%

    No Known Activations