© 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. 40252
    Prev
    Next
    INDEX
    Explanations

    have been

    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
    ä¸ĢæŶ
    -0.08
    onal
    -0.08
    åĪĨãģij
    -0.07
    wski
    -0.07
     spoke
    -0.07
    ebra
    -0.07
    dddd
    -0.07
    ä¸Ģçľĭ
    -0.07
     redhead
    -0.06
    çĿ
    -0.06
    POSITIVE LOGITS
     been
    0.13
    htag
    0.10
    htags
    0.10
    /is
    0.09
     become
    0.09
    been
    0.08
    htable
    0.08
     successfully
    0.08
    /she
    0.08
    esu
    0.08
    Activations Density 0.559%

    No Known Activations