© 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. 50349
    Prev
    Next
    INDEX
    Explanations

    baseball player descriptions

    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
    è°¬
    -0.10
    éŁŃ
    -0.09
    æ©¡
    -0.09
    ISTER
    -0.09
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
    æłijæŀĹ
    -0.08
    éļıä¹ĭ
    -0.08
    æ°Ķ象
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    åħ¨ç¤¾ä¼ļ
    -0.08
    POSITIVE LOGITS
    ores
    0.10
    Convention
    0.09
    çªģåĩºéĹ®é¢ĺ
    0.09
    äºī
    0.08
    empor
    0.08
    大ä¼ļ
    0.08
    èĦĤ
    0.08
    åħ¬æŃ£
    0.08
    _INV
    0.08
    åĬ²
    0.08
    Activations Density 0.069%

    No Known Activations