© 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. 9169
    Prev
    Next
    INDEX
    Explanations

    game mechanics like quests and movement

    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
    ä¸įçĪ±
    -0.09
     ÑģкаÑĩ
    -0.09
    abee
    -0.09
     Yoshi
    -0.09
    è¿«
    -0.09
    æľĹ
    -0.08
    æŃ»è§Ĵ
    -0.08
    涧
    -0.08
    笼
    -0.08
    è´Łè´£åIJĮå¿Ĺ
    -0.08
    POSITIVE LOGITS
    éĿĽ
    0.08
    .Keyword
    0.08
    çĻ½è¡£
    0.08
    è¸ıåħ¥
    0.08
    NIL
    0.08
    ä¸īå±Ĥ
    0.08
    åIJĪä¸Ģ
    0.08
    磫
    0.08
    _PROM
    0.08
    é«ĺè´¨éĩı
    0.08
    Activations Density 0.078%

    No Known Activations