© 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. 11413
    Prev
    Next
    INDEX
    Explanations

    freedom of

    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
    Ø©
    -0.13
    ation
    -0.10
    ryption
    -0.09
    วรรษ
    -0.09
    itivity
    -0.09
    fél
    -0.09
     lót
    -0.09
    adow
    -0.09
    cione
    -0.09
    ody
    -0.09
    POSITIVE LOGITS
    度çļĦ
    0.08
    s
    0.08
    ality
    0.08
    ships
    0.08
    sh
    0.08
    mente
    0.08
    raries
    0.08
    ts
    0.07
    estyle
    0.07
    er
    0.07
    Activations Density 0.008%

    No Known Activations