© 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. 62315
    Prev
    Next
    INDEX
    Explanations

    typedef struct

    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
    ened
    -0.09
    éģĹçĹĩ
    -0.09
    eres
    -0.09
    istic
    -0.09
    ¬ģ
    -0.08
    /or
    -0.08
    hund
    -0.08
    borough
    -0.08
    عة
    -0.08
    ui
    -0.08
    POSITIVE LOGITS
    ลฯ
    0.08
    ï¸ı
    0.07
    ï¸İ
    0.07
    antly
    0.07
    ENCE
    0.07
    ång
    0.07
    Ø©
    0.07
    dzie
    0.07
    een
    0.07
    ently
    0.07
    Activations Density 0.004%

    No Known Activations