© 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. 5590
    Prev
    Next
    INDEX
    Explanations

    face to face with

    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
    ÙĨد
    -0.09
    kov
    -0.09
     Haus
    -0.08
    ÙĨس
    -0.08
    abit
    -0.08
    _READONLY
    -0.08
    åı®
    -0.08
    å¥ı
    -0.08
    éĢĶ
    -0.08
    ç©°
    -0.08
    POSITIVE LOGITS
    éĿ¢å¯¹
    0.23
    éĿ¢å°į
    0.18
    éĿ¢ä¸´
    0.16
     facing
    0.14
     confrontation
    0.14
     faced
    0.14
    Facing
    0.14
     enfrent
    0.14
     confronted
    0.13
    éĿ¢ä¸´çĿĢ
    0.13
    Activations Density 0.038%

    No Known Activations