© 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. 54403
    Prev
    Next
    INDEX
    Explanations

    a day

    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¸ĢåĪĩéĥ½
    -0.10
    ä¸ĢåĪĩ
    -0.09
    æĦıè§ģåıįé¦Ī
    -0.09
    ·»
    -0.08
     prototype
    -0.08
    æħµ
    -0.08
    Own
    -0.08
    uling
    -0.08
    并æĹł
    -0.08
     prototypes
    -0.08
    POSITIVE LOGITS
    è¿Ļå¼ł
    0.10
    æľīä»»ä½ķ
    0.10
     Ø¥ÙĦا
    0.10
    nesc
    0.09
    央
    0.09
    åĿı
    0.09
    çļ±
    0.09
    è§ĴèIJ½
    0.09
     EVER
    0.09
    except
    0.09
    Activations Density 0.045%

    No Known Activations