© 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. 58169
    Prev
    Next
    INDEX
    Explanations

    untreated, control, none, Off, no

    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
    èıģ
    -0.07
    bable
    -0.07
    ä¸įåģľ
    -0.07
    biet
    -0.06
    RITE
    -0.06
    lica
    -0.06
    æľīå¿ħè¦ģ
    -0.06
    pson
    -0.06
    èĭ±ä¿Ĭ
    -0.06
    RC
    -0.06
    POSITIVE LOGITS
     protected
    0.07
    ä¸Ńå¿ĥçļĦ
    0.07
    peech
    0.07
    éĿ¢ç§¯ä¸º
    0.07
     Protected
    0.07
    onium
    0.07
    zion
    0.07
    ลุ
    0.07
    çĶ³æĺİ
    0.06
    protected
    0.06
    Activations Density 0.031%

    No Known Activations