© 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. 58703
    Prev
    Next
    INDEX
    Explanations

    baseball positions

    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
     ÑģамоÑģÑĤоÑı
    -0.10
    祸
    -0.09
    åĩĦ
    -0.09
    åħ¬åħ±æĸĩåĮĸ
    -0.09
    è¿Ŀæ³ķè¿Ŀè§Ħ
    -0.09
    LAG
    -0.09
    åŁł
    -0.08
    è§īæĤŁ
    -0.08
    åĪ¸
    -0.08
    ç¿ħ
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĬĬ
    0.11
    å½ĵä¹ĭ
    0.08
    çijķ
    0.08
     pu
    0.08
    沸èħ¾
    0.08
    çĻ½è¡£
    0.08
    æݪæĸ½
    0.08
    çĻĸ
    0.08
    SJ
    0.08
    ingo
    0.08
    Activations Density 0.004%

    No Known Activations