© 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. 62488
    Prev
    Next
    INDEX
    Explanations

    Lastly, finally

    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
    ä¹Łæľīå¾Īå¤ļ
    -0.10
    社ä¼ļåıijå±ķ
    -0.10
    年纪
    -0.10
    çĪ¨
    -0.10
    ä¼Ĭå§ĭ
    -0.09
    çŀ¬
    -0.08
    icult
    -0.08
    oir
    -0.08
    äºĨ好åĩł
    -0.08
    è·¬
    -0.08
    POSITIVE LOGITS
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.11
    å¸ĮæľĽå¤§å®¶
    0.11
    Lastly
    0.10
     Lastly
    0.10
     importantly
    0.10
    arily
    0.10
    æľĢéĩįè¦ģçļĦ
    0.10
    è¦ģ注æĦı
    0.09
    onas
    0.09
    finally
    0.09
    Activations Density 0.021%

    No Known Activations