© 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. 42508
    Prev
    Next
    INDEX
    Explanations

    objective function, linear coefficient

    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
    qip
    -0.07
    hn
    -0.07
    æ²¥
    -0.06
    éħĿ
    -0.06
    esh
    -0.06
     cata
    -0.06
    ç»Ī身
    -0.06
    Perm
    -0.06
    çļĦè´¨éĩı
    -0.06
    Ç
    -0.06
    POSITIVE LOGITS
    线æĢ§
    0.08
    å¹£
    0.08
    ç³»æķ°
    0.08
     Linear
    0.08
    linear
    0.08
     linear
    0.08
     coefficient
    0.07
    iett
    0.07
    Linear
    0.07
     pesos
    0.07
    Activations Density 0.004%

    No Known Activations