© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50366
    Prev
    Next
    INDEX
    Explanations

    according 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
    tings
    -0.10
    xed
    -0.10
    tering
    -0.10
    çĶ¨æĪ·æıIJä¾Ľ
    -0.10
    å°ĨæĿ¥
    -0.09
    coil
    -0.09
    ÑĤоÑĢ
    -0.09
    fully
    -0.09
    ë¡Ń
    -0.09
    bulk
    -0.09
    POSITIVE LOGITS
    ly
    0.11
    sWith
    0.11
    al
    0.10
    ed
    0.10
    emente
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.09
    entifier
    0.09
    alin
    0.09
    Ùģت
    0.09
    ness
    0.09
    Activations Density 0.048%

    No Known Activations