© 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. 43916
    Prev
    Next
    INDEX
    Explanations

    special characters and code comments

    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
    ehu
    -0.07
    leon
    -0.07
    ât
    -0.06
    ase
    -0.06
    çİī
    -0.06
    å¾Īå¤ļéĹ®é¢ĺ
    -0.06
    ложением
    -0.06
    jep
    -0.06
     hold
    -0.06
    ложениÑı
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    .TypeOf
    0.08
    ricos
    0.07
    ITED
    0.07
    彬
    0.07
    tori
    0.07
    æµ·åĮº
    0.07
    zio
    0.07
    çĹħæĥħæııè¿°
    0.07
    urna
    0.07
    Activations Density 0.002%

    No Known Activations