© 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. 47470
    Prev
    Next
    INDEX
    Explanations

    titles starting with "How" or "The"

    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
    æĢª
    -0.08
    âĢ¦”
    -0.08
    habi
    -0.08
     ode
    -0.07
    âĢ¦]
    -0.07
    .removeClass
    -0.07
    ĮĢ
    -0.07
    ”âĢ¦
    -0.07
    âĢ¦*
    -0.07
    âĢ¦the
    -0.07
    POSITIVE LOGITS
    çĮľä½łåĸľæ¬¢
    0.07
    pector
    0.06
    owie
    0.06
    uchs
    0.06
    s
    0.06
    ½ij
    0.06
    umps
    0.06
    _s
    0.06
    ¦
    0.06
    umus
    0.06
    Activations Density 0.545%

    No Known Activations