© 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. 46136
    Prev
    Next
    INDEX
    Explanations

    more details or info

    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
     simplest
    -0.08
    æľĢç®Ģåįķ
    -0.08
     easiest
    -0.07
     оÑĩеÑĢед
    -0.07
    ella
    -0.07
    亲æľĭ
    -0.07
    Ấ
    -0.07
    aviest
    -0.07
     hardest
    -0.07
    缸åºĶçļĦ
    -0.06
    POSITIVE LOGITS
     details
    0.13
     detail
    0.11
    ç»ĨèĬĤ
    0.11
    _than
    0.11
    detail
    0.11
    details
    0.10
     than
    0.10
    oom
    0.10
     Details
    0.10
     détails
    0.10
    Activations Density 0.190%

    No Known Activations