© 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. 28123
    Prev
    Next
    INDEX
    Explanations

    uninstall, remove, delete

    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
     tard
    -0.10
    .len
    -0.09
    леп
    -0.09
    _ep
    -0.09
    ided
    -0.08
    è±ķ
    -0.08
    åĴ¸
    -0.08
    encent
    -0.08
    EMENT
    -0.08
    èİ«åIJįåħ¶å¦Ļ
    -0.08
    POSITIVE LOGITS
    éĩįæĸ°
    0.11
    çĦ¶åIJİåĨį
    0.11
    ä¸ĢåįĬ
    0.10
    çİ°æľīçļĦ
    0.10
    ä¸ĢåĪĩ
    0.10
    ãģĮãĤī
    0.10
    æŧ
    0.10
     old
    0.10
    并对
    0.10
    old
    0.09
    Activations Density 0.290%

    No Known Activations