© 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. 2628
    Prev
    Next
    INDEX
    Explanations

    class loading errors

    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
    åªĴ
    -0.11
     RCS
    -0.10
    vsp
    -0.09
    èĨº
    -0.09
    utes
    -0.09
    æĢĢæĬ±
    -0.09
    æĿŀ
    -0.08
    .requires
    -0.08
    ystick
    -0.08
    马åĪº
    -0.08
    POSITIVE LOGITS
    è¾Ł
    0.08
    嵬
    0.08
     widen
    0.08
    顽
    0.08
    .detach
    0.08
    æĿ¿åĿĹ
    0.08
    èĬĤ课
    0.08
    çŃ¹
    0.08
    ť
    0.08
    é³į
    0.08
    Activations Density 0.286%

    No Known Activations