© 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. 20122
    Prev
    Next
    INDEX
    Explanations

    names of places and things

    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
     (
    -0.07
    vs
    -0.07
    ä¸ĭåľº
    -0.07
    vv
    -0.06
    vh
    -0.06
     bakal
    -0.06
     عÙħاÙĨ
    -0.06
    ukes
    -0.06
     {{{
    -0.06
     vs
    -0.06
    POSITIVE LOGITS
    ,...
    0.10
    ,âĢ¦
    0.10
    ettagli
    0.09
    Dettagli
    0.09
    ...**
    0.09
    "...
    0.09
     [...]
    0.09
    ...,
    0.09
    Leia
    0.08
     [âĢ¦]
    0.08
    Activations Density 0.106%

    No Known Activations