© 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. 40863
    Prev
    Next
    INDEX
    Explanations

    .Com elements

    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
     Batal
    -0.07
    UILD
    -0.06
    fü
    -0.06
    以ä¸ĭåĩłä¸ª
    -0.06
    _BITS
    -0.06
    以ä¸ĭåĩł
    -0.06
    åİĨ代
    -0.06
    idential
    -0.06
    Emitter
    -0.06
     buff
    -0.06
    POSITIVE LOGITS
    δή
    0.07
     ment
    0.07
    aux
    0.07
    dert
    0.06
     hers
    0.06
    oto
    0.06
    oges
    0.06
    imen
    0.06
     fict
    0.06
    uite
    0.06
    Activations Density 0.044%

    No Known Activations