© 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. 33432
    Prev
    Next
    INDEX
    Explanations

    fractions or numbers

    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
     army
    -0.07
    &m
    -0.07
    eid
    -0.06
    %p
    -0.06
    çĻ¾åĪĨä¹ĭ
    -0.06
    enko
    -0.06
    ëĭ´
    -0.06
    eneral
    -0.06
     Joc
    -0.06
    acro
    -0.06
    POSITIVE LOGITS
    bruch
    0.08
    icals
    0.07
    åħ°çī¹
    0.07
    coce
    0.07
    oggio
    0.07
    éricas
    0.07
    errupted
    0.07
    rof
    0.07
    reck
    0.07
    etros
    0.07
    Activations Density 0.014%

    No Known Activations