© 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. 26434
    Prev
    Next
    INDEX
    Explanations

    units and values

    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
     ezek
    -0.06
    è±Ĩ
    -0.06
    ubb
    -0.06
    å·¦
    -0.06
    acking
    -0.06
    hta
    -0.06
    oma
    -0.06
    owie
    -0.06
    åĪĴè¿ĩ
    -0.06
     Associated
    -0.06
    POSITIVE LOGITS
    _consts
    0.08
    该款
    0.08
    å®ĥæīĢ
    0.07
     pouc
    0.07
    -regexp
    0.07
    åħ¨éĥ¨åĨħ容
    0.07
    åݿ人
    0.07
    anst
    0.07
     cadr
    0.07
    .inst
    0.07
    Activations Density 0.001%

    No Known Activations