© 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. 43935
    Prev
    Next
    INDEX
    Explanations

    pathway or ase

    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
    estiv
    -0.07
    keit
    -0.07
     manti
    -0.07
    iaux
    -0.06
    immutable
    -0.06
    opor
    -0.06
    è·¯æ¼Ķ
    -0.06
    rew
    -0.06
    åªĽ
    -0.06
    åħ¥äºĨ
    -0.06
    POSITIVE LOGITS
    大å°Ĩ
    0.07
    Ø«
    0.07
    è¿ĩç¨ĭ
    0.06
    ggio
    0.06
    ivr
    0.06
    ÙĪØ«
    0.06
     оÑĤда
    0.06
     Jeff
    0.06
    赶
    0.06
    net
    0.06
    Activations Density 0.001%

    No Known Activations