© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14369
    Prev
    Next
    INDEX
    Explanations

    complete example

    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
    jenigen
    -0.11
    ske
    -0.10
    oops
    -0.09
    zelf
    -0.09
    bers
    -0.09
    gnore
    -0.09
    uken
    -0.09
    sche
    -0.08
    schen
    -0.08
    ught
    -0.08
    POSITIVE LOGITS
    å®Įæķ´çļĦ
    0.09
    zza
    0.08
    -bodied
    0.08
    itud
    0.08
    cy
    0.07
    ãģĭãģ¤
    0.07
    erton
    0.07
    ly
    0.07
    èµ·è§ģ
    0.07
    issima
    0.07
    Activations Density 0.007%

    No Known Activations