© 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. 20965
    Prev
    Next
    INDEX
    Explanations

    text adventure game directions

    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
    åIJĮæŃ¥
    -0.11
    ufe
    -0.10
    åĮĿ
    -0.09
    .Sync
    -0.09
     Gat
    -0.09
    帰
    -0.09
    åĬ¿
    -0.09
    ç®Ķ
    -0.09
    æĪĺ绩
    -0.09
    é£İçŃĿ
    -0.09
    POSITIVE LOGITS
    è½®
    0.10
    大æ´ĭ
    0.09
    é²µ
    0.09
    æݨçIJĨ
    0.09
    è£ħä¿®
    0.08
    宾é¦Ĩ
    0.08
    inspect
    0.08
    exe
    0.08
     Hint
    0.08
    ä½ı
    0.08
    Activations Density 0.071%

    No Known Activations