© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51585
    Prev
    Next
    INDEX
    Explanations

    words starting with ap

    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
    tat
    -0.09
    iest
    -0.09
    eren
    -0.09
    angle
    -0.09
    aight
    -0.09
    æłī
    -0.09
    pedia
    -0.08
    æĢģ
    -0.08
    念
    -0.08
    æªĹ
    -0.08
    POSITIVE LOGITS
    pearance
    0.13
    -ap
    0.11
    erture
    0.10
    (ap
    0.10
    plied
    0.10
    æīĭåĬ¿
    0.09
    gar
    0.09
    ä¸ľè¥¿
    0.09
    /ap
    0.09
    itra
    0.09
    Activations Density 0.073%

    No Known Activations