© 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. 27007
    Prev
    Next
    INDEX
    Explanations

    adventures and adventure followed by related nouns

    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
    icer
    -0.09
    enstein
    -0.09
    ael
    -0.09
    æ·¡æ·¡çļĦ
    -0.08
     damage
    -0.08
    æĥħåĨµä¸ĭ
    -0.08
    çī©è´¨
    -0.08
    人寿
    -0.08
    çĶŁæĹ¥
    -0.08
    åįļä¼ļ
    -0.08
    POSITIVE LOGITS
    æĤł
    0.10
    hip
    0.10
    agger
    0.09
    ously
    0.09
    anzi
    0.09
    anter
    0.09
     Ellison
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    urous
    0.09
    WithIdentifier
    0.08
    Activations Density 0.009%

    No Known Activations