© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8596
    Prev
    Next
    INDEX
    Explanations

    directory listing

    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
    绳
    -0.09
    åºľ
    -0.09
    ðŁı»
    -0.09
    çĸ«æĥħå½±åĵį
    -0.08
    cape
    -0.08
    ãģ£ãģ±
    -0.08
    appable
    -0.08
    cents
    -0.08
    ä»ĸä»¬åľ¨
    -0.08
    çıij
    -0.08
    POSITIVE LOGITS
    ihan
    0.10
    è¿ŀäºij
    0.10
    games
    0.10
    izon
    0.09
    ways
    0.09
    .Directory
    0.09
    åĨħçļĦ
    0.09
    Õ¾
    0.09
    orent
    0.09
    zelf
    0.09
    Activations Density 0.033%

    No Known Activations