© 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. 30995
    Prev
    Next
    INDEX
    Explanations

    application, continuation, assigned

    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
    éĢ¡
    -0.10
    GridLayout
    -0.10
    ç»Ī
    -0.09
    æ¯Ĵåĵģ
    -0.09
    使æĪij
    -0.09
    .jupiter
    -0.08
    /dr
    -0.08
    ICollectionView
    -0.08
    èĩªè´Ł
    -0.08
    çķ¥æľī
    -0.08
    POSITIVE LOGITS
    éĽħ
    0.10
    ä»°
    0.10
    ÑĢок
    0.09
    åįģéĩĮ
    0.09
    åľ¬
    0.08
    èĬľ
    0.08
    æŀĿ
    0.08
    ouro
    0.08
    æijĩ
    0.08
    深交æīĢ
    0.08
    Activations Density 0.614%

    No Known Activations