© 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. 32481
    Prev
    Next
    INDEX
    Explanations

    Marine Corps, Mercedes-Benz

    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
    æĿ²
    -0.11
    çĽį
    -0.09
    ebra
    -0.09
    éĢļ车
    -0.09
    家ä¼Ļ
    -0.09
    IMUM
    -0.09
    广çĶµ
    -0.08
    è§ģè¿ĩ
    -0.08
    anism
    -0.08
     Berg
    -0.08
    POSITIVE LOGITS
    éĺ´å½±
    0.10
     Crate
    0.09
    uckle
    0.09
     кÑĢÑĥ
    0.09
    社交
    0.09
    ä¸įåĨį
    0.08
    olon
    0.08
    ippo
    0.08
    cka
    0.08
    å¹ķ
    0.08
    Activations Density 0.007%

    No Known Activations