© 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. 39275
    Prev
    Next
    INDEX
    Explanations

    proximity and distance

    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
    åķĨæĬ¥
    -0.08
    å½ĵä¹ĭ
    -0.08
    vron
    -0.08
    éĨī
    -0.08
    æģĥ
    -0.08
    ç²ķ
    -0.08
    æ¾Ħ
    -0.08
    -mini
    -0.08
    ãĥĨãĤ£
    -0.08
    ç»ĻåĪ«äºº
    -0.08
    POSITIVE LOGITS
    åĴ«
    0.20
    è·Ŀ离
    0.20
    ä¸įè¿ľ
    0.18
    è·ĿéĽ¢
    0.17
     close
    0.16
    æİ¥è¿ij
    0.15
     proximity
    0.15
    çļĦè·Ŀ离
    0.15
     Close
    0.14
    close
    0.14
    Activations Density 0.086%

    No Known Activations