© 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. 40458
    Prev
    Next
    INDEX
    Explanations

    amphibian

    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
     Äijâm
    -0.07
    çł´æµª
    -0.07
    çįħ
    -0.07
    天使
    -0.07
     Santa
    -0.07
    Ñħол
    -0.07
     Adler
    -0.07
    ariat
    -0.07
     Ferrari
    -0.07
    ipop
    -0.07
    POSITIVE LOGITS
    èĭĶ
    0.10
     moss
    0.10
    湿润
    0.09
     Frog
    0.09
     amphib
    0.08
     frogs
    0.08
    湿度
    0.08
    keys
    0.07
    InstanceOf
    0.07
    湿
    0.07
    Activations Density 0.027%

    No Known Activations