© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8185
    Prev
    Next
    INDEX
    Explanations

    student debt, loans, and witchcraft

    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
    hazi
    -0.10
    对æĪij
    -0.08
    plist
    -0.08
    ç¿ħèĨĢ
    -0.08
    é¹ŀ
    -0.08
    -spe
    -0.08
    ಡ
    -0.08
    .Expect
    -0.08
    subclass
    -0.08
    åĽ½ç±į
    -0.08
    POSITIVE LOGITS
    æijĦ
    0.11
    æ¶ķ
    0.09
    夫
    0.09
    éĢĢ
    0.09
    èľľ
    0.09
    arth
    0.09
    åĬ©éķ¿
    0.08
    isse
    0.08
    quip
    0.08
    è¿Ħä»Ĭ
    0.08
    Activations Density 0.007%

    No Known Activations