© 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. 10537
    Prev
    Next
    INDEX
    Explanations

    gene development and patterning

    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
    éij«
    -0.07
    ilon
    -0.07
     neglig
    -0.07
     rated
    -0.07
     teor
    -0.06
    æŁ¥
    -0.06
     Goodman
    -0.06
    è¶
    -0.06
     interceptor
    -0.06
    ysz
    -0.06
    POSITIVE LOGITS
    åıijèĤ²
    0.10
    å¾ĪæĹ©å°±
    0.09
     patter
    0.09
    Ø·Ùģ
    0.09
    early
    0.09
     developmental
    0.09
    èĥļèĥİ
    0.08
     orchestr
    0.08
     inheritance
    0.08
     lineage
    0.08
    Activations Density 0.188%

    No Known Activations