© 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. 47845
    Prev
    Next
    INDEX
    Explanations

    until ... (more information)

    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
     precedenza
    -0.08
    лл
    -0.08
    èĢĮå¤į
    -0.07
    å¿ħ
    -0.07
    esto
    -0.07
    оди
    -0.07
    istere
    -0.07
    nik
    -0.07
    utto
    -0.07
    Äįe
    -0.07
    POSITIVE LOGITS
    /if
    0.09
     someone
    0.08
    /how
    0.07
    /un
    0.07
    为æŃ¢
    0.07
    åĨįä¹Ł
    0.07
     they
    0.07
     somebody
    0.07
    _=
    0.07
    åĵªå¤©
    0.07
    Activations Density 0.043%

    No Known Activations