© 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. 64600
    Prev
    Next
    INDEX
    Explanations

    Putname ember

    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
     Ving
    -0.08
    /sl
    -0.07
     Somm
    -0.07
    å½±åĵįçĿĢ
    -0.07
    lick
    -0.07
    èݽ
    -0.06
    illot
    -0.06
     intellig
    -0.06
    orem
    -0.06
    éĿ©åij½çļĦ
    -0.06
    POSITIVE LOGITS
    insky
    0.08
    аниÑİ
    0.07
     easing
    0.07
    åİŁæĸĩåĩºå¤Ħ
    0.07
    åĽłåħ¬
    0.07
    ании
    0.07
    horn
    0.07
    æľīåħ³äºĭ项
    0.07
    iana
    0.06
    eht
    0.06
    Activations Density 0.015%

    No Known Activations