© 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. 2155
    Prev
    Next
    INDEX
    Explanations

    the three words

    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
    auer
    -0.08
    详æĥħ
    -0.06
    arn
    -0.06
    éĿ©
    -0.06
    orthy
    -0.06
    imat
    -0.06
    :`
    -0.06
    ium
    -0.06
    å¿ħ
    -0.06
    ä¸įåı¯æĢĿè®®
    -0.06
    POSITIVE LOGITS
    第äºĮéĥ¨åĪĨ
    0.10
     latter
    0.10
    åīįèĢħ
    0.09
    第ä¸Ģ项
    0.09
    umerator
    0.09
    åIJİèĢħ
    0.09
    第ä¸Ģéĥ¨åĪĨ
    0.09
     denominator
    0.08
     terms
    0.08
     secondi
    0.08
    Activations Density 0.036%

    No Known Activations