© 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. 17113
    Prev
    Next
    INDEX
    Explanations

    private internal

    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
    eprom
    -0.07
    -indent
    -0.07
    दà¥įर
    -0.07
    trag
    -0.07
    REMOTE
    -0.07
    lep
    -0.07
    جت
    -0.06
    uman
    -0.06
    oris
    -0.06
    ledon
    -0.06
    POSITIVE LOGITS
     internal
    0.13
     Internal
    0.12
     internals
    0.12
     internally
    0.12
    internal
    0.12
    Internal
    0.12
    /internal
    0.11
    åĨħéĥ¨
    0.11
    .Internal
    0.11
    çļĦåĨħéĥ¨
    0.11
    Activations Density 0.182%

    No Known Activations