© 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. 31126
    Prev
    Next
    INDEX
    Explanations

    "the" followed by chief descriptors

    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
    ä¸ĢäºĽ
    -0.10
    çļĦä¸ĢäºĽ
    -0.10
    ä¸ĢæµģçļĦ
    -0.09
    çĵł
    -0.09
    æĬĦ
    -0.09
    çĶ³
    -0.09
    isce
    -0.09
    incer
    -0.08
    inkel
    -0.08
    åĪĽå®¢
    -0.08
    POSITIVE LOGITS
    主è¦ģåİŁåĽł
    0.11
    ä¸įå¾Ĺå·²
    0.10
     reason
    0.09
     пÑĢиÑĩ
    0.09
    LOAT
    0.09
    éĩįè¦ģåİŁåĽł
    0.09
    ult
    0.08
    é£İæ³¢
    0.08
    atures
    0.08
    è¿ĻæĶ¯
    0.08
    Activations Density 0.093%

    No Known Activations