© 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. 12168
    Prev
    Next
    INDEX
    Explanations

    supersaturation and solvent

    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
    shal
    -0.08
    å¥ł
    -0.08
    ç¿»æĸ°
    -0.07
    áĥĺáĥĽ
    -0.07
    åIJĥéĨĭ
    -0.07
    è£ĺ
    -0.07
    воÑĢÑı
    -0.07
     Balt
    -0.07
    md
    -0.07
    ystone
    -0.07
    POSITIVE LOGITS
     зака
    0.08
    çĬ¶æĢģ
    0.08
    uper
    0.08
    缴èĩ³
    0.08
    .getState
    0.07
    缴åĪ°
    0.07
    åŃķèĤ²
    0.07
     dolu
    0.07
    çĬ¶æĢģçļĦ
    0.07
    yota
    0.07
    Activations Density 0.005%

    No Known Activations