© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8968
    Prev
    Next
    INDEX
    Explanations

    credit score

    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
    OrCreate
    -0.10
    秩
    -0.09
    ophon
    -0.09
    æijĩæ»ļ
    -0.09
    KHR
    -0.09
    oldt
    -0.08
    èĻļæŀĦ
    -0.08
    ä»»ä½ķä¸Ģ个
    -0.08
     Geneva
    -0.08
    æ¸Ķæ°ij
    -0.08
    POSITIVE LOGITS
    åĪ©å¥½
    0.10
    æ·¡æ·¡
    0.09
    åī¯æľ¬
    0.09
    æ³Ľ
    0.09
    åĸĿ
    0.09
    ä¿Ĺ称
    0.08
    ftype
    0.08
    çĹĴ
    0.08
    .Endpoint
    0.08
    legate
    0.08
    Activations Density 0.001%

    No Known Activations