© 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. 57550
    Prev
    Next
    INDEX
    Explanations

    Harry Potter or 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
    æ²Ĩ
    -0.11
    ç½į
    -0.10
    èĩªå¸¦
    -0.10
    æħ·
    -0.09
    ITES
    -0.09
    strap
    -0.09
     Nug
    -0.09
    ANGE
    -0.09
    大家åĪĨ享
    -0.09
     Sunder
    -0.09
    POSITIVE LOGITS
    诸èijĽ
    0.10
    åĪĿä¸ī
    0.09
    éĢĨ
    0.09
    鸢
    0.08
    çłĶåĪ¶
    0.08
    æĬµ
    0.08
    ãĤ¾
    0.07
    7
    0.07
    uros
    0.07
    æľī趣
    0.07
    Activations Density 0.039%

    No Known Activations