© 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. 12861
    Prev
    Next
    INDEX
    Explanations

    models and specific names

    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
    ruf
    -0.08
    bian
    -0.08
    AMPLE
    -0.08
    anit
    -0.08
     Kalim
    -0.08
     Pew
    -0.07
    éĺ¿æĭī伯
    -0.07
    çĺ«
    -0.07
    çĸ²è½¯
    -0.07
     Polyester
    -0.07
    POSITIVE LOGITS
    模åŀĭ
    0.09
     model
    0.09
    模åŀĭçļĦ
    0.08
    model
    0.08
     Bohr
    0.08
    Model
    0.07
    -era
    0.07
     models
    0.07
    -model
    0.07
     Model
    0.07
    Activations Density 0.001%

    No Known Activations