© 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. 11635
    Prev
    Next
    INDEX
    Explanations

    "or""or" or "and"

    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
    æ½ĭ
    -0.10
     confronting
    -0.09
    æİ°
    -0.09
    tin
    -0.09
    ะ
    -0.08
    ä¸įå¿į
    -0.08
    æĦı大
    -0.08
    åĬ¨æīĭ
    -0.08
    èĬĿ
    -0.08
    ago
    -0.08
    POSITIVE LOGITS
    èĩªä»İ
    0.09
    nia
    0.09
     bur
    0.09
    UPER
    0.09
    çĮ·
    0.09
    æ´Ľåħĭ
    0.08
    upal
    0.08
    sizeof
    0.08
    andi
    0.08
    benh
    0.08
    Activations Density 0.009%

    No Known Activations