© 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. 28899
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical notation

    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
    Dat
    -0.08
    ail
    -0.07
     prop
    -0.07
    åħ³å¿ĥ
    -0.06
    çĥŃ
    -0.06
    arith
    -0.06
    .ar
    -0.06
     Dat
    -0.06
    IX
    -0.06
    cs
    -0.06
    POSITIVE LOGITS
     didik
    0.08
    ogia
    0.08
    ÙĦاء
    0.08
    oggio
    0.08
    ÐķÐļ
    0.07
    ekten
    0.07
    _TW
    0.07
    engah
    0.07
    reten
    0.07
     tuá»ķi
    0.07
    Activations Density 0.003%

    No Known Activations