© 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. 33406
    Prev
    Next
    INDEX
    Explanations

    Conan names

    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
    ingly
    -0.12
    å¥Ĥ
    -0.09
    ãĥ³ãĤ°
    -0.09
    zelf
    -0.09
    cripts
    -0.09
     LOSS
    -0.09
    orem
    -0.09
    ppers
    -0.09
    LOSS
    -0.09
    ssi
    -0.08
    POSITIVE LOGITS
    æĻ¨æĬ¥
    0.10
    ä¸Ĭåīį
    0.10
    ÑĢ
    0.09
    ition
    0.09
    gra
    0.09
    Ø°
    0.08
    åĭĥ
    0.08
    زاد
    0.08
    ç»ıæŁ¥
    0.08
     Ñģвоего
    0.08
    Activations Density 0.005%

    No Known Activations