© 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. 41397
    Prev
    Next
    INDEX
    Explanations

    separation processes

    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
     cifra
    -0.08
    Mapped
    -0.08
     Ramp
    -0.07
    TemplateName
    -0.07
    çĹĽ
    -0.07
    对åĨħ
    -0.07
     bÅij
    -0.07
    åľ°åĽ¾
    -0.07
    æī©å¼ł
    -0.07
     ramp
    -0.07
    POSITIVE LOGITS
    åĪĨå±Ĥ
    0.13
     strat
    0.11
     sediment
    0.10
    åºķéĥ¨
    0.10
    æ²īéĻį
    0.09
     segregation
    0.09
     vertical
    0.09
    åºķéĥ¨çļĦ
    0.09
     bottom
    0.09
    æĤ¬æµ®
    0.09
    Activations Density 0.033%

    No Known Activations