© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38108
    Prev
    Next
    INDEX
    Explanations

    Honda cars and Honduran places

    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
    ../../../
    -0.10
    ../../
    -0.10
    rior
    -0.09
    ãģĦãģŁãĤī
    -0.09
    леÑĩ
    -0.09
    趴
    -0.09
    IES
    -0.09
    ÑģÑĤв
    -0.08
    ears
    -0.08
    IBC
    -0.08
    POSITIVE LOGITS
    ry
    0.11
    OCR
    0.10
    ancy
    0.10
    forth
    0.09
    ина
    0.09
    áĢı
    0.09
    åľŃ
    0.09
    że
    0.09
    ément
    0.09
    sworth
    0.09
    Activations Density 0.017%

    No Known Activations