© 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. 10691
    Prev
    Next
    INDEX
    Explanations

    tag:message structure

    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
    çŃĶ
    -0.07
    Âł
    -0.06
    atee
    -0.06
    estina
    -0.06
    âĢ
    -0.06
    â
    -0.06
    -0.06
    athy
    -0.06
    ina
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
    edException
    0.08
    ?}",
    0.08
    lanjut
    0.07
     Folg
    0.07
    defs
    0.07
    clave
    0.07
    edImage
    0.07
    ëĭ¤ê°Ģ
    0.07
    çĻ¾éĩĮ
    0.07
    ussen
    0.07
    Activations Density 0.012%

    No Known Activations