© 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. 34894
    Prev
    Next
    INDEX
    Explanations

    mistake or trap

    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
    Encoded
    -0.07
     pal
    -0.07
    pal
    -0.07
    _pick
    -0.06
    _GENERIC
    -0.06
    anes
    -0.06
     cus
    -0.06
     Bea
    -0.06
     outnumber
    -0.06
    _predicate
    -0.06
    POSITIVE LOGITS
    误åĮº
    0.11
    è¿ĩ度
    0.11
     overly
    0.10
    çŃīä¸įèī¯
    0.10
    à¹Ģà¸ģิà¸Ļà¹Ħà¸Ľ
    0.10
    çĭŃéļĺ
    0.09
    çīĩéĿ¢
    0.09
     misguided
    0.09
    lessly
    0.09
    å¦Ħ
    0.09
    Activations Density 0.059%

    No Known Activations