© 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. 57307
    Prev
    Next
    INDEX
    Explanations

    counting down or up

    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
    anga
    -0.07
    è¿Ľåİ»äºĨ
    -0.06
    ettle
    -0.06
     lạc
    -0.06
    atics
    -0.06
    kol
    -0.06
    μÏĨ
    -0.06
     context
    -0.06
    umbu
    -0.06
    æĬļ
    -0.06
    POSITIVE LOGITS
    ãĤ¼ãĥŃ
    0.09
    .zero
    0.09
     Zero
    0.09
    鼶
    0.09
    éĻįèĩ³
    0.09
    ZERO
    0.09
     zero
    0.08
    ngu
    0.08
    Zero
    0.08
    .ZERO
    0.08
    Activations Density 0.010%

    No Known Activations