© 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. 31520
    Prev
    Next
    INDEX
    Explanations

    reality check

    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
    ηÏĥη
    -0.09
     ÑĢода
    -0.09
    leden
    -0.08
     rahasia
    -0.08
    prendre
    -0.08
    ezen
    -0.07
    esian
    -0.07
    alam
    -0.07
    aide
    -0.07
    ForResult
    -0.07
    POSITIVE LOGITS
    istically
    0.12
    istic
    0.12
    ationship
    0.11
    -world
    0.09
    -life
    0.09
    ģ
    0.08
    umbo
    0.08
    åĨĻçħ§
    0.08
    ISTIC
    0.08
    é¨ĵ
    0.08
    Activations Density 0.043%

    No Known Activations