© 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. 18506
    Prev
    Next
    INDEX
    Explanations

    x a variables

    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
     disen
    -0.07
    upu
    -0.07
    break
    -0.07
    çĴ¨
    -0.07
    tokens
    -0.07
     Sip
    -0.06
     dew
    -0.06
    liest
    -0.06
    comun
    -0.06
    .breakpoints
    -0.06
    POSITIVE LOGITS
    endt
    0.09
    åŀĤ缴
    0.08
    缴è§Ĵ
    0.08
     horizontal
    0.08
     perpendicular
    0.08
    utum
    0.08
    amor
    0.07
    Caller
    0.07
    tan
    0.07
    缴
    0.07
    Activations Density 0.006%

    No Known Activations