© 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. 29170
    Prev
    Next
    INDEX
    Explanations

    ranking 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
    ob
    -0.09
    en
    -0.07
    ÏĢοÏį
    -0.07
    اب
    -0.07
    aut
    -0.07
    ieg
    -0.06
    ANG
    -0.06
    æĸ½æķij
    -0.06
    id
    -0.06
    ok
    -0.06
    POSITIVE LOGITS
    íĺ¹
    0.08
    -vars
    0.08
    renz
    0.08
    odata
    0.08
    orz
    0.07
    orks
    0.07
    leve
    0.07
    onsor
    0.07
    _frag
    0.07
    edul
    0.07
    Activations Density 0.038%

    No Known Activations