© 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. 57723
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
     dec
    -0.10
    èļĵ
    -0.08
    çī
    -0.08
    å¼±åĬ¿
    -0.08
    sig
    -0.08
    dec
    -0.08
    noinspection
    -0.08
     Sig
    -0.08
    æīįå¹²
    -0.08
    _ENUM
    -0.08
    POSITIVE LOGITS
    çĸ¯
    0.10
    OMEM
    0.09
    èį¡
    0.09
    ÑĢажа
    0.09
    lander
    0.09
    鸣
    0.09
    bour
    0.09
    زاÙĦ
    0.09
    Await
    0.09
     Pandora
    0.09
    Activations Density 0.227%

    No Known Activations