© 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. 58570
    Prev
    Next
    INDEX
    Explanations

    asset:name

    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
    s
    -0.10
    succ
    -0.07
    à¥Ģल
    -0.07
    p
    -0.07
    pq
    -0.07
    spect
    -0.07
    es
    -0.07
    ori
    -0.07
     cul
    -0.07
    ever
    -0.07
    POSITIVE LOGITS
    E
    0.10
    T
    0.08
    L
    0.08
    èse
    0.08
    ï¸İ
    0.08
    R
    0.08
    O
    0.08
    stellung
    0.07
    ousel
    0.07
    EV
    0.07
    Activations Density 0.016%

    No Known Activations