© 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. 7388
    Prev
    Next
    INDEX
    Explanations

    reiterated or repeated statements

    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
    akis
    -0.09
     fus
    -0.08
    åĽŀçŃĶ
    -0.08
    5
    -0.08
    andin
    -0.08
    8
    -0.08
    3
    -0.08
    ä¸ĢæĬĬ
    -0.08
    9
    -0.08
     actually
    -0.08
    POSITIVE LOGITS
    ä¸Ģéģį
    0.12
    äºĨä¸Ģéģį
    0.12
    åįģå¹´åīį
    0.11
    åĿļå®ļ
    0.10
    åĪĿå¿ĥ
    0.10
    两年åīį
    0.10
    ç»ıåħ¸çļĦ
    0.10
    ä¸Ĭè°ĥ
    0.10
    pch
    0.10
    ä¼ļéķ¿
    0.10
    Activations Density 0.013%

    No Known Activations