© 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. 50507
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    éĵ¡
    -0.12
    æ¯Ľ
    -0.10
    odom
    -0.10
    交æĺĵ
    -0.10
    åıªä¸įè¿ĩ
    -0.09
    ä¸įåĬ¨
    -0.09
    Shortcut
    -0.09
    çĤķ
    -0.09
    æľĪä¸ĭ
    -0.09
    (cols
    -0.09
    POSITIVE LOGITS
    åī¥
    0.10
    æł¸åĩĨ
    0.10
    å¤ĩæ¡Ī
    0.08
    åīĬ
    0.08
    æŀģéĻIJ
    0.08
    éĻįèĩ³
    0.08
    çīĻ
    0.08
    å³ĭ
    0.08
    meric
    0.08
    åį°åĪ·
    0.08
    Activations Density 0.107%

    No Known Activations