© 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. 8233
    Prev
    Next
    INDEX
    Explanations

    led by

    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
    ity
    -0.11
    lod
    -0.10
    åħ´ä¸ļ
    -0.10
    ãĤº
    -0.09
    openh
    -0.09
    aus
    -0.09
    ãģĹãĤĩãģĨ
    -0.08
    пиÑģаÑĤÑĮ
    -0.08
    ably
    -0.08
    poss
    -0.08
    POSITIVE LOGITS
    gers
    0.12
    Ùij
    0.12
    ãģĹãģı
    0.11
    gable
    0.10
    rence
    0.10
    ìį¨
    0.09
    itud
    0.09
    кÑģ
    0.09
    ngth
    0.09
    éģ½
    0.09
    Activations Density 0.018%

    No Known Activations