© 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. 15290
    Prev
    Next
    INDEX
    Explanations

    emotional states and well-being

    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
     Postar
    -0.09
    enner
    -0.09
    ecker
    -0.08
    гни
    -0.08
    adore
    -0.08
    ({_
    -0.08
    dera
    -0.08
    azor
    -0.08
    rebs
    -0.08
    éĽ·é¸£
    -0.08
    POSITIVE LOGITS
    åĽłç´łå½±åĵį
    0.07
     motiv
    0.07
    oto
    0.06
    士æ°Ķ
    0.06
    idis
    0.06
    主è§Ĥ
    0.06
     morale
    0.06
    åıĬæĬĢæľ¯
    0.06
    åĴĮæĬĢæľ¯
    0.06
    hu
    0.06
    Activations Density 0.248%

    No Known Activations