© 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. 57009
    Prev
    Next
    INDEX
    Explanations

    analysis and context

    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
    ErrorMsg
    -0.09
    ниÑĩеÑģÑĤво
    -0.09
     Ristor
    -0.08
    armo
    -0.08
    ç¦Ħ
    -0.08
    eyed
    -0.08
    鬣
    -0.08
    交æĬķ
    -0.08
    cky
    -0.08
     Postar
    -0.08
    POSITIVE LOGITS
    iner
    0.07
     examples
    0.07
     problems
    0.07
     L
    0.06
     a
    0.06
    ä¸Ģä¾ĭ
    0.06
    çIJĨ论ä¸İå®ŀè·µ
    0.06
     Key
    0.06
     Case
    0.06
    éĢļæ°Ķ
    0.06
    Activations Density 0.466%

    No Known Activations