© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21488
    Prev
    Next
    INDEX
    Explanations

    accomplishments and achievements

    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
    ernet
    -0.10
    èĭĹ
    -0.10
    严èĤĥ
    -0.10
    éĴ¤
    -0.10
    /rfc
    -0.10
    èĩªçĦ¶èµĦæºIJ
    -0.09
    èŀįåIJĪåıijå±ķ
    -0.09
    ä¿¡èµĸ
    -0.09
    误ä¼ļ
    -0.09
     Hud
    -0.09
    POSITIVE LOGITS
    æĪIJå°±
    0.17
     feat
    0.17
     feats
    0.16
     achievements
    0.15
     accomplish
    0.14
     accomplishments
    0.14
    accom
    0.14
     accomplished
    0.14
     Accom
    0.14
     accomplishment
    0.13
    Activations Density 0.085%

    No Known Activations