© 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. 24863
    Prev
    Next
    INDEX
    Explanations

    blocks/rotten_bark

    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
    ster
    -0.07
    æ¡Ī
    -0.06
    ier
    -0.06
    ition
    -0.06
    ero
    -0.06
    ÑģÑĤва
    -0.06
    ↵↵
    -0.06
    -
    -0.06
     manifest
    -0.06
    nier
    -0.05
    POSITIVE LOGITS
    áĢŃáĢ¯
    0.09
    å©ķ
    0.09
    sig
    0.08
    akedown
    0.08
    okable
    0.08
    ignet
    0.08
     pera
    0.08
    _lineno
    0.07
     vén
    0.07
    ajari
    0.07
    Activations Density 0.001%

    No Known Activations