© 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. 23867
    Prev
    Next
    INDEX
    Explanations

    articles, citation, Q

    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
    eria
    -0.08
    essler
    -0.07
    pren
    -0.07
    设为é¦ĸ页
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    bsolute
    -0.07
    å®ŀè¯Ŀ
    -0.07
    æĪĸå°ij
    -0.07
    etwork
    -0.07
    μή
    -0.07
    POSITIVE LOGITS
    umped
    0.07
    VPN
    0.07
     γε
    0.06
    åįĬå²Ľ
    0.06
    TRY
    0.06
    abstract
    0.06
    ARC
    0.06
    ikit
    0.06
     decltype
    0.06
    uks
    0.06
    Activations Density 0.001%

    No Known Activations