© 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. 11261
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    amac
    -0.09
    常æĢģåĮĸ
    -0.08
    oba
    -0.08
    almaz
    -0.08
    áh
    -0.08
    ematik
    -0.07
    illard
    -0.07
    omatic
    -0.07
    arde
    -0.07
    agre
    -0.07
    POSITIVE LOGITS
    pointer
    0.07
    注å°Ħ
    0.07
    _CAST
    0.07
    è·Łåľ¨
    0.06
    ijk
    0.06
    _STORAGE
    0.06
    注å¡ij
    0.06
    pron
    0.06
    æĭĶåĩº
    0.06
    .tf
    0.06
    Activations Density 0.000%

    No Known Activations