© 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. 32582
    Prev
    Next
    INDEX
    Explanations

    substitution

    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
    è¿ģ
    -0.08
     ukr
    -0.08
    ultas
    -0.08
    anos
    -0.07
    jes
    -0.07
     koal
    -0.07
    æ±Ľ
    -0.07
    ekt
    -0.07
    à¤ķार
    -0.07
    åĬ
    -0.07
    POSITIVE LOGITS
    代åħ¥
    0.11
    ä»£æĽ¿
    0.10
    æĽ¿æį¢
    0.10
     substitution
    0.10
     substitutions
    0.09
     substit
    0.09
     substitute
    0.09
     substitutes
    0.09
    åıĸ代
    0.09
     replacing
    0.08
    Activations Density 0.016%

    No Known Activations