© 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. 55161
    Prev
    Next
    INDEX
    Explanations

    Mitt Romney

    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
    hips
    -0.10
    ein
    -0.10
    icip
    -0.08
    ection
    -0.08
     reign
    -0.08
    漫
    -0.08
    ees
    -0.08
    å«Ĥ
    -0.08
    THING
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    eling
    0.09
    _gap
    0.09
    笤
    0.09
    许
    0.09
    resents
    0.09
    绫
    0.09
    Spo
    0.08
     victorious
    0.08
    uous
    0.08
    izen
    0.08
    Activations Density 0.001%

    No Known Activations