© 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. 36376
    Prev
    Next
    INDEX
    Explanations

    feminist icon, mythology, artist, pioneer

    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
    inston
    -0.09
    bur
    -0.09
    ../../../
    -0.08
    vine
    -0.08
    ç¹ģ
    -0.08
    ulty
    -0.08
    追究
    -0.08
    ä¸ĵ人
    -0.08
    amera
    -0.08
     pand
    -0.08
    POSITIVE LOGITS
    iske
    0.11
    wik
    0.10
    å©¿
    0.10
    бил
    0.10
    istas
    0.10
    ä¾£
    0.09
     поÑģÑĤоÑı
    0.09
    主ä¹īèĢħ
    0.09
    è§Ĵ度æĿ¥çľĭ
    0.09
    ateful
    0.09
    Activations Density 0.012%

    No Known Activations