© 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. 40168
    Prev
    Next
    INDEX
    Explanations

    loading and progress indicators

    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
     ressort
    -0.09
    åīªè£ģ
    -0.09
    /Layout
    -0.08
    çķħæīĢ欲è¨Ģ
    -0.08
    翼翼
    -0.08
    onton
    -0.08
    .osgi
    -0.08
     ç§ģ
    -0.07
     dì
    -0.07
    chter
    -0.07
    POSITIVE LOGITS
    è¿Ľåº¦
    0.13
     progress
    0.13
    éĢ²åº¦
    0.12
     Progress
    0.12
    progress
    0.11
    Progress
    0.10
    .Progress
    0.10
    请èĢIJå¿ĥçŃīå¾ħ
    0.10
    _progress
    0.10
     completion
    0.10
    Activations Density 0.190%

    No Known Activations