© 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. 2561
    Prev
    Next
    INDEX
    Explanations

    speed up

    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
    è¾Ī
    -0.09
    è¾ĵ
    -0.09
    ansa
    -0.09
    abouts
    -0.09
     è¾ĵ
    -0.08
    åĪĽéĢłæĢ§
    -0.08
    ä¸Ģç¯ĩ
    -0.08
    驺
    -0.08
    稳å®ļçļĦ
    -0.08
    饱满
    -0.08
    POSITIVE LOGITS
    tributes
    0.10
    vious
    0.09
    Thin
    0.09
    tribute
    0.09
    rick
    0.09
    à°³
    0.09
    梵
    0.08
    kok
    0.08
    åIJŁ
    0.08
    ijk
    0.08
    Activations Density 0.011%

    No Known Activations