© 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. 31763
    Prev
    Next
    INDEX
    Explanations

    Controller

    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
    ä¸Ģä¸ĭå°±
    -0.07
    pret
    -0.07
    voi
    -0.07
    .bp
    -0.06
    ×ķ×ĸ
    -0.06
    bpp
    -0.06
    zew
    -0.06
     Lees
    -0.06
    atti
    -0.06
    actice
    -0.06
    POSITIVE LOGITS
    ÅĻej
    0.07
    çīµ
    0.07
    ÙĦاÙģ
    0.06
    dete
    0.06
    åľ¨é©¬
    0.06
    ä¸ĩåĽ½
    0.06
    _dash
    0.06
     Ent
    0.06
    ä¸įæŃ£
    0.06
    atorie
    0.06
    Activations Density 0.132%

    No Known Activations