© 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. 30201
    Prev
    Next
    INDEX
    Explanations

    first visit or new to

    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
    åħ·ä½ĵçļĦ
    -0.08
    igram
    -0.08
    ableView
    -0.08
    eron
    -0.08
     bare
    -0.08
    çĩİ
    -0.08
    让人
    -0.08
    èĪĤ
    -0.08
    纲
    -0.08
    auss
    -0.08
    POSITIVE LOGITS
    asu
    0.09
    è¿ijå¹´æĿ¥
    0.08
    è¿ĻéĩĮæľī
    0.08
    illion
    0.08
    åIJĪä½ľä¼Ļä¼´
    0.08
    åłī
    0.08
    áĥij
    0.08
    plits
    0.08
    rish
    0.08
     اÙĪ
    0.08
    Activations Density 0.012%

    No Known Activations