© 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. 22598
    Prev
    Next
    INDEX
    Explanations

    objects and their properties

    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
    wich
    -0.10
    abouts
    -0.09
    ľ
    -0.09
    roots
    -0.09
    loe
    -0.09
    ез
    -0.09
    -up
    -0.09
    vero
    -0.09
    grounds
    -0.09
    رج
    -0.09
    POSITIVE LOGITS
    ives
    0.20
    ive
    0.14
    ivity
    0.14
    IVES
    0.12
    ively
    0.11
    swith
    0.11
    ivec
    0.11
    à¸Ľà¸£à¸°à¸ªà¸ĩ
    0.11
    ekt
    0.10
    sWith
    0.10
    Activations Density 0.087%

    No Known Activations