© 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. 49779
    Prev
    Next
    INDEX
    Explanations

    my own

    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
    èĩªå·±çļĦ
    -0.10
    umas
    -0.10
    ouse
    -0.09
    éĤ£äºº
    -0.09
    ãģ¨ãĤĤ
    -0.09
    ä»ĸèĩªå·±
    -0.09
    ouro
    -0.08
     Burke
    -0.08
    å¿ĺ
    -0.08
    azi
    -0.08
    POSITIVE LOGITS
    ständ
    0.11
    çĭ¬çī¹çļĦ
    0.10
     behalf
    0.10
    verständlich
    0.10
    krit
    0.09
    iable
    0.09
    åĭº
    0.09
     sÃłng
    0.09
    iet
    0.09
    çĭ¬çī¹
    0.09
    Activations Density 0.026%

    No Known Activations