© 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. 32703
    Prev
    Next
    INDEX
    Explanations

    dependency name or property

    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
    arsed
    -0.08
    anita
    -0.07
    uit
    -0.07
    åħįåİ»
    -0.07
    alp
    -0.06
    åĪ°çĽ®åīį
    -0.06
    akhir
    -0.06
    resents
    -0.06
    å¿ĺ
    -0.06
    vert
    -0.06
    POSITIVE LOGITS
    aston
    0.07
    ä½ĵèĤ²ä¸Ńå¿ĥ
    0.07
    ↵↵↵↵↵↵
    0.07
    nese
    0.06
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    0.06
     Rubio
    0.06
    hö
    0.06
    aiss
    0.06
    reira
    0.06
    миÑı
    0.06
    Activations Density 0.011%

    No Known Activations