© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50162
    Prev
    Next
    INDEX
    Explanations

    induction development risk

    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
    æĭīå¾·
    -0.07
     reci
    -0.06
    ang
    -0.06
    (PDO
    -0.06
     forms
    -0.06
    nese
    -0.06
    ÙĪÙĪ
    -0.06
    rac
    -0.06
    ha
    -0.06
     NOI
    -0.06
    POSITIVE LOGITS
    irting
    0.08
    vr
    0.08
    alsy
    0.08
    ideos
    0.08
    ido
    0.07
    lr
    0.07
    irt
    0.07
     Leng
    0.07
    æĥ¬
    0.07
    opoly
    0.07
    Activations Density 0.483%

    No Known Activations