© 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. 17640
    Prev
    Next
    INDEX
    Explanations

    photos of myself, family, or Roger

    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
    osa
    -0.13
    yt
    -0.11
    åķĨåѦéĻ¢
    -0.10
    stay
    -0.10
    ocos
    -0.10
    ymm
    -0.10
    鸡汤
    -0.09
    èĹį
    -0.09
    ptr
    -0.09
    áĥ¤
    -0.09
    POSITIVE LOGITS
    åĬŀ好
    0.09
    ting
    0.09
    çĹ¼
    0.09
     yourself
    0.09
    è¿Ī
    0.09
    ÙĪاÙĨ
    0.08
     herself
    0.08
    ç¼ħ
    0.08
    cape
    0.08
    cial
    0.08
    Activations Density 0.071%

    No Known Activations