© 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. 27494
    Prev
    Next
    INDEX
    Explanations

    `S1` `S2` struct leads board IDs

    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
    zb
    -0.07
    vb
    -0.06
    etc
    -0.06
    çŃīæݪæĸ½
    -0.06
    çŃīæīĭ段
    -0.06
    ç´¢èµĶ
    -0.06
     etc
    -0.05
    çĪ½å¿«
    -0.05
    @include
    -0.05
     Malk
    -0.05
    POSITIVE LOGITS
    _fps
    0.08
    ặng
    0.07
    orz
    0.07
     ÙĪجÙĩ
    0.07
     setFrame
    0.07
    åı²
    0.07
    alten
    0.07
    essages
    0.07
    å°±ä¸ļæľºä¼ļ
    0.07
    athers
    0.07
    Activations Density 0.028%

    No Known Activations