© 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. 2118
    Prev
    Next
    INDEX
    Explanations

    email recipient marker

    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
    aus
    -0.08
     conserv
    -0.07
    engan
    -0.07
    ioso
    -0.07
     wacht
    -0.07
    è½°
    -0.06
    است
    -0.06
     dessus
    -0.06
    ãģŁãģ¾
    -0.06
    ŀ
    -0.06
    POSITIVE LOGITS
    atform
    0.07
    modifica
    0.07
    ingroup
    0.07
    chow
    0.07
    linger
    0.07
    ikum
    0.07
    çķ¥
    0.06
     regr
    0.06
    WAR
    0.06
     COMPR
    0.06
    Activations Density 0.026%

    No Known Activations