© 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. 39304
    Prev
    Next
    INDEX
    Explanations

    tables with numbers and 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
    ç¦Ħ
    -0.08
     }]
    -0.07
    icip
    -0.07
    Ø¡
    -0.06
    åĪ°å¤©
    -0.06
    lec
    -0.06
    xl
    -0.06
    .servlet
    -0.06
    etlen
    -0.06
    åħĨ
    -0.06
    POSITIVE LOGITS
    ANDOM
    0.07
    _rgba
    0.07
    俱ä¹IJéĥ¨
    0.07
     quarti
    0.07
     Fourth
    0.07
     omas
    0.07
    ç¬¬åĽĽ
    0.07
    Fourth
    0.07
    zana
    0.07
    fulness
    0.07
    Activations Density 0.087%

    No Known Activations