© 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. 62411
    Prev
    Next
    INDEX
    Explanations

    game movement and items

    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
    èĢ
    -0.09
    .gt
    -0.09
    çı©
    -0.09
    åħ¨å¤©
    -0.09
    ç»Ŀ
    -0.09
    çĦ¶æĺ¯
    -0.09
    ç¿Ĭ
    -0.08
     Jed
    -0.08
    åħ¨ç¨ĭ
    -0.08
    afil
    -0.08
    POSITIVE LOGITS
    æĶ¾å¤§
    0.11
    æĬ¬
    0.09
    æľĪä¸Ń
    0.09
    çļĦä¸įåIJĮ
    0.09
    使èĢħ
    0.09
    æijŃ
    0.09
    èĢģçĪ·
    0.09
    èģĮåijĺ
    0.08
    è½®åĽŀ
    0.08
    Void
    0.08
    Activations Density 0.099%

    No Known Activations