© 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. 55994
    Prev
    Next
    INDEX
    Explanations

    pH values and numbers

    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
    çĻ½éľ²
    -0.09
    /rs
    -0.08
     знако
    -0.08
    kus
    -0.08
    rics
    -0.08
    øl
    -0.08
    زÙĩ
    -0.08
    ignan
    -0.08
    ä¸Ģå¤ľ
    -0.08
    _PLAN
    -0.08
    POSITIVE LOGITS
    Âł
    0.08
    设置为
    0.07
    ç«Ń
    0.07
    åĵģ
    0.06
    强çĥĪ
    0.06
    ä¸ĵéŨ
    0.06
    defer
    0.06
    ï½ŀãĢĤ
    0.06
    å¼·çĥĪ
    0.06
    ensi
    0.06
    Activations Density 0.535%

    No Known Activations