© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    regarding concerning about

    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
    åľ¨äº¬
    -0.10
    isser
    -0.10
    okers
    -0.09
    åľ¨å¹¿å·ŀ
    -0.09
    unker
    -0.09
    perms
    -0.09
    çĴľ
    -0.09
    alem
    -0.09
    isers
    -0.09
    seeing
    -0.09
    POSITIVE LOGITS
    åħ³äºİ
    0.19
     regarding
    0.17
    éĹľæĸ¼
    0.13
     concerning
    0.12
     Regarding
    0.11
     tentang
    0.11
     about
    0.10
     vá»ģ
    0.10
     بشأÙĨ
    0.10
     toward
    0.09
    Activations Density 0.142%

    No Known Activations