© 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. 31311
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters

    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
    atos
    -0.09
    led
    -0.07
    esto
    -0.07
    atot
    -0.07
    ato
    -0.07
    anto
    -0.07
    ATO
    -0.06
    ØŃت
    -0.06
    说起
    -0.06
    quiv
    -0.06
    POSITIVE LOGITS
    ãģ©ãģĵãĤį
    0.09
    åģļèĩªå·±
    0.08
    decorators
    0.08
    monds
    0.08
    ankan
    0.08
    orer
    0.08
    ×ķרת
    0.08
    ãĥŃãĥĥ
    0.08
    å®Ĺ主
    0.07
    ughs
    0.07
    Activations Density 0.049%

    No Known Activations