© 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. 48049
    Prev
    Next
    INDEX
    Explanations

    sequences like '3n' or '2 n'

    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
    LOS
    -0.08
    SES
    -0.06
    ASP
    -0.06
    _TUN
    -0.06
    amá
    -0.06
    ä¸İç»´æĬ¤
    -0.06
    çŃij
    -0.06
    寿
    -0.06
     |/
    -0.06
    iddles
    -0.06
    POSITIVE LOGITS
     Paar
    0.08
    ottes
    0.07
    åĮºäººæ°ijæĶ¿åºľ
    0.07
    ánh
    0.07
    ElementType
    0.07
    quot
    0.07
    çĥ
    0.07
    对çĻ½
    0.07
    åĽ¾éĽĨ
    0.07
    èIJ½åľ°
    0.07
    Activations Density 0.020%

    No Known Activations