© 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. 21418
    Prev
    Next
    INDEX
    Explanations

    specific characters or code delimiters

    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
    akil
    -0.09
    .IsActive
    -0.08
    ctica
    -0.08
    abar
    -0.08
     {_
    -0.08
    urah
    -0.08
     (*((
    -0.07
    agrid
    -0.07
     {.
    -0.07
    rekli
    -0.07
    POSITIVE LOGITS
    çŃīçŃī
    0.09
    追
    0.06
    ãģªãģ©
    0.06
    èµ°
    0.06
    缸åħ³æ³ķå¾ĭ责任
    0.06
    ody
    0.06
     bref
    0.06
    MD
    0.06
    eda
    0.06
    çħ§
    0.06
    Activations Density 0.016%

    No Known Activations