© 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. 46725
    Prev
    Next
    INDEX
    Explanations

    code comments or separators

    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
    -0.09
    ãģįãģ®
    -0.08
    檸
    -0.08
    cript
    -0.08
    relude
    -0.07
    ç¢į
    -0.07
    ünsch
    -0.07
    ikle
    -0.07
    ically
    -0.07
    aka
    -0.07
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.07
    OTE
    0.07
    osal
    0.07
    arov
    0.06
    éĽģ
    0.06
    arden
    0.06
    éģĵéģĵ
    0.06
    anto
    0.06
    çĵ£
    0.06
    åĭĩå¾Ģ缴åīį
    0.06
    Activations Density 0.037%

    No Known Activations