© 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. 47623
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
    _SEPARATOR
    -0.08
    ocate
    -0.08
    aju
    -0.08
    allen
    -0.07
    ocas
    -0.07
    oca
    -0.07
    EEK
    -0.07
    ookie
    -0.07
    å®īå±ħ
    -0.07
    пиÑĤа
    -0.07
    POSITIVE LOGITS
    uwd
    0.08
    issant
    0.07
    zak
    0.07
    isl
    0.07
    ubin
    0.07
    åħĭæĭī
    0.07
    åį«çĶŁåĴĮ
    0.07
    idla
    0.07
     Casc
    0.07
    illing
    0.07
    Activations Density 0.016%

    No Known Activations