© 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. 57657
    Prev
    Next
    INDEX
    Explanations

    Clark names and related 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
    å¤§éĽ¨
    -0.13
    รา
    -0.11
    å¾Ĺèµ·
    -0.11
    eenth
    -0.10
    ราว
    -0.10
    acher
    -0.10
    ÖĦ
    -0.10
    ancock
    -0.09
    heimer
    -0.09
    Õ²
    -0.09
    POSITIVE LOGITS
    ../../../
    0.16
    -eyed
    0.10
    enstein
    0.09
    -cut
    0.09
    ãģ¯ãģļ
    0.08
    виÑĤ
    0.08
    ready
    0.08
    usters
    0.08
    à¹īà¸Ńย
    0.08
    worthy
    0.08
    Activations Density 0.012%

    No Known Activations