© 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. 40277
    Prev
    Next
    INDEX
    Explanations

    axis or axial direction

    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
    å¾·éŁ³
    -0.08
    anzi
    -0.08
    hini
    -0.08
    ENAME
    -0.08
    isca
    -0.07
    /respond
    -0.07
    enal
    -0.07
    å¿ĥçĹĽ
    -0.07
    çĹħäºĨ
    -0.07
    å½¢å¼ıå¤ļæł·
    -0.07
    POSITIVE LOGITS
    主轴
    0.10
    轴线
    0.10
     axis
    0.09
    åŀĤ缴
    0.09
    éĶ¥
    0.09
    è½´åIJij
    0.09
    _axis
    0.09
    è½´
    0.08
    æĿŁ
    0.08
    -axis
    0.08
    Activations Density 0.019%

    No Known Activations