© 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. 25081
    Prev
    Next
    INDEX
    Explanations

    costa

    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
    çļĦ产çĶŁ
    -0.07
    nets
    -0.07
    kert
    -0.06
     Palme
    -0.06
    parm
    -0.06
    AKE
    -0.06
    容
    -0.06
    çļĦåıijçĶŁ
    -0.06
    FromString
    -0.06
    æĭħ
    -0.06
    POSITIVE LOGITS
     near
    0.12
    å±Ģéĥ¨
    0.12
     everywhere
    0.11
    å±Ģéĥ¨çļĦ
    0.11
     wherever
    0.11
    åľ¨æŁIJäºĽ
    0.11
    çī¹åĪ«æĺ¯åľ¨
    0.10
    åľ¨è¿ĻäºĽ
    0.10
    对äºİè¿ĻäºĽ
    0.10
    å°¤åħ¶æĺ¯åľ¨
    0.10
    Activations Density 0.362%

    No Known Activations