© 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. 17012
    Prev
    Next
    INDEX
    Explanations

    option selections

    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
    s
    -0.09
     –
    -0.07
     dri
    -0.06
    ition
    -0.06
     "
    -0.06
    å°ij
    -0.06
    太
    -0.06
    !
    -0.06
     Organ
    -0.06
    —
    -0.06
    POSITIVE LOGITS
    çĭ¬åѤ
    0.09
    çijŀæĭī
    0.09
    imed
    0.09
    ãĥĥãĤ¿
    0.08
    Singleton
    0.08
    langs
    0.08
     rajav
    0.08
    aths
    0.08
    ambang
    0.08
    _REUSE
    0.08
    Activations Density 0.003%

    No Known Activations