© 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. 27947
    Prev
    Next
    INDEX
    Explanations

    lambda expressions, CoffeeScript, statistically significant, ImmutableJS, luent, transition, utf, doubles

    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
    agan
    -0.07
    igan
    -0.07
     itself
    -0.07
    该产åĵģ
    -0.07
    hear
    -0.07
     Pud
    -0.07
    igate
    -0.07
    hai
    -0.07
    apres
    -0.07
    _own
    -0.07
    POSITIVE LOGITS
    æ£ł
    0.06
    çĦ¦
    0.06
    ç¿ģ
    0.06
    arit
    0.06
    ocal
    0.06
    opes
    0.06
    åħħ
    0.06
    åĨ³ç®Ĺ
    0.06
     hit
    0.06
    owl
    0.06
    Activations Density 0.043%

    No Known Activations