© 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. 53433
    Prev
    Next
    INDEX
    Explanations

    community-based

    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
    /cards
    -0.08
    åĿı
    -0.08
    èĥľ
    -0.08
    _locals
    -0.08
    /thumb
    -0.08
    success
    -0.08
    lect
    -0.08
    åĦ¿å¥³
    -0.08
    ACS
    -0.08
    ä¹İ
    -0.08
    POSITIVE LOGITS
    强æľīåĬĽçļĦ
    0.10
    éľ°
    0.10
    çĨ¨
    0.09
    榻
    0.09
    屿
    0.08
    åĨĮ
    0.08
    çĪ±åĽ½ä¸»ä¹ī
    0.08
    çĵ®
    0.08
    .removeFrom
    0.08
    å«£
    0.08
    Activations Density 0.017%

    No Known Activations