© 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. 38650
    Prev
    Next
    INDEX
    Explanations

    game state or position

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.10
    åĪĨæĺİ
    -0.09
    çķĻè¨ĢæĿ¿
    -0.09
    æľĢåħ³éĶ®
    -0.09
    forward
    -0.09
    éģij
    -0.09
    iser
    -0.09
    讫
    -0.08
    åħĪ导
    -0.08
    ness
    -0.08
    POSITIVE LOGITS
    éĩĮçļĦ
    0.09
    åĨħçļĦ
    0.09
    ows
    0.08
     Lamb
    0.08
    顺åĬ¿
    0.08
    LM
    0.08
    çªĸ
    0.08
    owe
    0.08
    å°ıåŀĭ
    0.08
     damit
    0.08
    Activations Density 0.001%

    No Known Activations