© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32043
    Prev
    Next
    INDEX
    Explanations

    hash table .id key string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghan
    -0.08
    åħħåĪĨä½ĵçİ°äºĨ
    -0.07
    .Std
    -0.07
    lh
    -0.07
    katan
    -0.07
    etts
    -0.07
    æĸ¯é¡¿
    -0.07
    _sources
    -0.07
    临港
    -0.07
    swick
    -0.07
    POSITIVE LOGITS
    æĬķ
    0.08
    frequ
    0.07
    unique
    0.07
    ENA
    0.07
    å½Ĵ
    0.07
     discret
    0.07
     unique
    0.07
    æĬ½è±¡
    0.07
    å½Ĵäºİ
    0.07
     Roe
    0.07
    Activations Density 0.043%

    No Known Activations