© 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. 19272
    Prev
    Next
    INDEX
    Explanations

    eliminated or out

    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
    /apis
    -0.10
    è¿ĩåĪĨ
    -0.10
    åħħæ²Ľ
    -0.09
    ÑģÑĤо
    -0.09
    ãĤĵãģª
    -0.09
    鼷æĸ¯
    -0.09
    åħħ足
    -0.09
    åı£è¢ĭ
    -0.09
    侮辱
    -0.09
    URN
    -0.09
    POSITIVE LOGITS
    åĩºå±Ģ
    0.18
    æ·ĺæ±°
    0.18
    被æ·ĺæ±°
    0.16
    éĢĢåĩº
    0.12
    æİī
    0.12
    æ±°
    0.10
    æİīäºĨ
    0.10
     bow
    0.09
     cast
    0.09
    èĴ
    0.09
    Activations Density 0.069%

    No Known Activations