© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35939
    Prev
    Next
    INDEX
    Explanations

    player's role

    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¡Įæĥħ
    -0.09
    æĪijæĬĬ
    -0.09
    yre
    -0.09
    ardi
    -0.09
    jam
    -0.08
     revision
    -0.08
    èħ´
    -0.08
     ÑģпеÑĨиалÑĮно
    -0.08
    è¦ģ害
    -0.08
    è®®é¢ĺ
    -0.08
    POSITIVE LOGITS
    æī®æ¼Ķ
    0.13
    åı¯ä»¥éĢīæĭ©
    0.11
    çļĦè§Ĵèī²
    0.10
    å§Ķå®£ä¼łéĥ¨
    0.10
    è§Ĵèī²
    0.09
    äºĶ大
    0.09
    çĸı
    0.09
    ·æĸ°
    0.09
    çļĦä»»åĬ¡
    0.09
    绣é¢Ĩ
    0.09
    Activations Density 0.092%

    No Known Activations