© 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. 11450
    Prev
    Next
    INDEX
    Explanations

    messages you never sent

    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
    æĦİ
    -0.09
    诱
    -0.09
    омеÑĢ
    -0.09
    éĿ©
    -0.09
    趣åij³
    -0.09
    秧
    -0.09
    elib
    -0.09
    åı¯çĸij
    -0.09
    é¤į
    -0.08
    è´¼
    -0.08
    POSITIVE LOGITS
    泪
    0.14
    æĦŁåĬ¨
    0.13
    触åĬ¨
    0.13
    åĵ½
    0.12
    家åºŃæķĻèĤ²
    0.12
    åħ¬çĽĬ
    0.11
    潸
    0.11
    æīĵåĬ¨
    0.11
    çľ¼æ³ª
    0.11
    æĦŁè§¦
    0.11
    Activations Density 0.214%

    No Known Activations