© 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. 31171
    Prev
    Next
    INDEX
    Explanations

    DVD player or version

    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
    oft
    -0.11
    lessly
    -0.10
    o
    -0.10
    æı©
    -0.09
    chaft
    -0.09
    åįģ足
    -0.09
    ä¸ĭçıŃ
    -0.09
    ively
    -0.09
    adamente
    -0.08
    ×ķת
    -0.08
    POSITIVE LOGITS
    -ROM
    0.10
    çĨ
    0.10
    illo
    0.09
    åĪ»
    0.09
    برÙĬ
    0.09
    prog
    0.09
    alter
    0.08
    pies
    0.08
    gor
    0.08
    ê°Ģìŀħ
    0.08
    Activations Density 0.006%

    No Known Activations