© 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. 18162
    Prev
    Next
    INDEX
    Explanations

    degrees, ml, %, numbers

    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
    shoot
    -0.07
    ola
    -0.07
     esattamente
    -0.07
    纶
    -0.07
    usi
    -0.06
    ryn
    -0.06
    æī¬éķ¿
    -0.06
    olum
    -0.06
    äºĮåįģä¹Ŀ
    -0.06
    享
    -0.06
    POSITIVE LOGITS
    typ
    0.10
     typical
    0.09
    å¹³åĿĩæ°´å¹³
    0.09
     Typical
    0.09
    åģĩ设
    0.08
    Typ
    0.08
    itore
    0.08
    anee
    0.08
    assume
    0.08
    åħ¸åŀĭçļĦ
    0.08
    Activations Density 0.030%

    No Known Activations