© 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. 34635
    Prev
    Next
    INDEX
    Explanations

    class hierarchy and relationships

    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
    oja
    -0.08
    å£ģä¸Ĭ
    -0.08
    jom
    -0.07
    cione
    -0.07
    ugno
    -0.07
    emm
    -0.07
    ammer
    -0.07
    leter
    -0.07
    geschrieben
    -0.07
     ÙħÙĪا
    -0.07
    POSITIVE LOGITS
    åħ³ç³»
    0.08
    è°¬
    0.08
    è¿Ļ个éģĵçIJĨ
    0.07
    etail
    0.07
    -to
    0.07
    åıĬéĥ¨åĪĨ
    0.07
    åħ³ç³»çļĦ
    0.07
    äºĭçī©çļĦ
    0.07
     relationships
    0.07
    Relation
    0.07
    Activations Density 0.019%

    No Known Activations