© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21677
    Prev
    Next
    INDEX
    Explanations

    x-axis and y-axis labels

    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
    onar
    -0.09
    _userdata
    -0.08
    beau
    -0.08
    æķĻèĤ²æĺ¯
    -0.07
    æķĻèĤ²ä¸İ
    -0.07
    éĵ¿
    -0.07
    å½°
    -0.07
    .hashCode
    -0.07
    лла
    -0.07
    åŃĺåľ¨äºİ
    -0.07
    POSITIVE LOGITS
     depicting
    0.07
     representing
    0.07
    è½´
    0.06
     ranging
    0.06
     représentant
    0.06
    een
    0.06
     labelled
    0.06
     measuring
    0.06
     quantity
    0.06
     axes
    0.06
    Activations Density 0.010%

    No Known Activations