© 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. 23289
    Prev
    Next
    INDEX
    Explanations

    int main, stainless steel, up arrow, .domain.com

    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
    Ł
    -0.08
    зÑĥ
    -0.07
    è·ĭ
    -0.07
    éħį
    -0.07
    мп
    -0.06
    Ĩ
    -0.06
    妮
    -0.06
    Emp
    -0.06
     Emp
    -0.06
    _TRI
    -0.06
    POSITIVE LOGITS
    opak
    0.07
     altrimenti
    0.07
    aket
    0.07
     otherwise
    0.07
    åŁºæķ°
    0.07
    quir
    0.07
    ancen
    0.07
    æĽ´åĬłåĬªåĬĽ
    0.07
    æĥķ
    0.07
    -scal
    0.07
    Activations Density 0.045%

    No Known Activations