© 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. 26699
    Prev
    Next
    INDEX
    Explanations

    property and data analysis

    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
     Pue
    -0.08
    esai
    -0.08
    大æŃ¥
    -0.07
    èĢĮå¾ĹåIJį
    -0.07
    为èį£
    -0.07
    iace
    -0.07
     οικον
    -0.07
    å¾·éŁ³
    -0.07
    åħ¶ä¹IJ
    -0.07
    .firebaseapp
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.08
    å°Ĩè¿ĻäºĽ
    0.07
    åľ¨è¿ĻäºĽ
    0.07
    estr
    0.06
    /
    0.06
    atri
    0.06
    ou
    0.06
    enberg
    0.06
    å¦Ĥæľī
    0.06
    Äĩi
    0.06
    Activations Density 0.022%

    No Known Activations