© 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. 17657
    Prev
    Next
    INDEX
    Explanations

    Âł followed by numbers or "Appe" or "Previous"

    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
    -0.15
    Ø©
    -0.12
    ting
    -0.11
    ़
    -0.09
    Ùĩ
    -0.09
    te
    -0.09
    ÄĻż
    -0.08
    ÑĢаÑī
    -0.08
    åĦ¿
    -0.08
    ELY
    -0.08
    POSITIVE LOGITS
    oused
    0.08
    deaux
    0.07
    ÅŁÄ±
    0.07
    nection
    0.07
    ominated
    0.07
    istic
    0.07
    thetic
    0.07
    à§įড
    0.07
    çļĦé¥®é£Ł
    0.07
    onsel
    0.07
    Activations Density 0.109%

    No Known Activations