© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    is followed by verb or adjective

    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
    IBA
    -0.09
    chw
    -0.09
    addir
    -0.08
    åħ¶æŀĹ
    -0.08
    ãģļãģ¤
    -0.07
    社åĨħ
    -0.07
    _race
    -0.07
    åħ¬åı¸åıijå±ķ
    -0.07
     Trento
    -0.07
    ếp
    -0.07
    POSITIVE LOGITS
    ohl
    0.07
    arians
    0.06
    ün
    0.06
     context
    0.06
    åľ¨æѤä¹ĭåīį
    0.06
     thus
    0.06
    ë¦Ħ
    0.06
     described
    0.06
    aren
    0.06
    ullet
    0.06
    Activations Density 0.099%

    No Known Activations