© 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. 13737
    Prev
    Next
    INDEX
    Explanations

    ratio followed by /

    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
    emps
    -0.08
     createAction
    -0.07
    صاد
    -0.07
    /vendors
    -0.07
    izons
    -0.07
    /*.
    -0.07
     highly
    -0.07
    iskus
    -0.07
    olith
    -0.07
    _GRE
    -0.07
    POSITIVE LOGITS
    cope
    0.07
     ê·¸ëłĩì§Ģ
    0.07
    åłĤçļĩ
    0.06
    Norm
    0.06
    .EntityFramework
    0.06
     ave
    0.06
    常æĢģ
    0.06
     Norm
    0.06
    åİŁæľī
    0.06
    è¤Ĥ
    0.06
    Activations Density 0.009%

    No Known Activations