© 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. 41437
    Prev
    Next
    INDEX
    Explanations

    cylinder bottom, perspective, hidden line

    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
    è¤Ĵ
    -0.07
    ron
    -0.07
    ers
    -0.07
    rock
    -0.06
     statement
    -0.06
     Statement
    -0.06
     random
    -0.06
     Leistung
    -0.06
    Statement
    -0.06
     target
    -0.06
    POSITIVE LOGITS
     rabat
    0.10
    åºĶ交
    0.10
    idian
    0.08
    æķ¬è¯·åħ³æ³¨
    0.08
    abox
    0.08
    quez
    0.08
    doch
    0.08
    æĶ¶äºİ
    0.08
    .yang
    0.08
    Normals
    0.08
    Activations Density 0.001%

    No Known Activations