© 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. 19063
    Prev
    Next
    INDEX
    Explanations

    endoplasmic reticulum or sarcoplasmic reticulum

    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
    emd
    -0.07
    inals
    -0.07
    设å¤ĩå®īè£ħ
    -0.07
    ÃŃf
    -0.07
     jamb
    -0.07
    èĢħ们
    -0.07
    BIND
    -0.07
    ##_
    -0.07
    ToLeft
    -0.07
    POSITIVE LOGITS
    ilha
    0.07
    åĢ¾
    0.07
    uzz
    0.07
    æ±
    0.07
    lightbox
    0.07
    haven
    0.06
    åħ¼
    0.06
    clearfix
    0.06
     Laurea
    0.06
    _DECLARE
    0.06
    Activations Density 0.050%

    No Known Activations