© 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. 23134
    Prev
    Next
    INDEX
    Explanations

    around or centered

    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
    anes
    -0.10
    请åıĬæŶ
    -0.09
    æĬ½
    -0.09
    æ¯ıæ¯ı
    -0.09
    è¦ģ说
    -0.09
    è¸ıåħ¥
    -0.09
    hausen
    -0.09
    _fsm
    -0.08
    åħ¨åŁŁ
    -0.08
    éĵĦ
    -0.08
    POSITIVE LOGITS
    åĽ´ç»ķ
    0.26
     around
    0.19
     вокÑĢÑĥг
    0.18
    Around
    0.16
    around
    0.16
     Around
    0.16
     autour
    0.15
    åĽ´çĿĢ
    0.15
    åľį
    0.14
    ç´§ç´§åĽ´ç»ķ
    0.14
    Activations Density 0.069%

    No Known Activations