© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52100
    Prev
    Next
    INDEX
    Explanations

    cell references with absolute addressing

    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
    Negative Logits
    s
    -0.07
    iez
    -0.07
    es
    -0.06
    ↵
    -0.06
     S
    -0.06
    éĢĤ
    -0.06
    ets
    -0.06
    era
    -0.06
    mer
    -0.05
    :
    -0.05
    POSITIVE LOGITS
    åħ¶æŀĹ
    0.09
    alloca
    0.09
    dealloc
    0.09
    çļ®ä¹¦
    0.08
    _OCCURRED
    0.08
    *“.
    0.08
    æ¡ĪçĶ±
    0.08
    èı²çī¹
    0.08
    abouts
    0.08
    онаÑĤ
    0.08
    Activations Density 0.004%

    No Known Activations