© 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. 32747
    Prev
    Next
    INDEX
    Explanations

    cellular differentiation

    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
    ansch
    -0.08
    åįķè¾¹
    -0.07
    ho
    -0.07
    å½ĵäºĭ人çļĦ
    -0.07
    rš
    -0.06
    æĸ°å©ļ
    -0.06
    å¨ģåĬĽ
    -0.06
     frequency
    -0.06
    çļĦåĬĽåº¦
    -0.06
    argar
    -0.06
    POSITIVE LOGITS
    åĪĨåĮĸ
    0.13
     lineage
    0.10
     clones
    0.10
     differentiation
    0.09
    åħĭéļĨ
    0.09
     phenotype
    0.08
     specialization
    0.08
    ä¸ĭä¸Ģéĺ¶æ®µ
    0.08
    ä¸įæŁĵ
    0.08
     recruited
    0.08
    Activations Density 0.165%

    No Known Activations