© 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. 31731
    Prev
    Next
    INDEX
    Explanations

    states of 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
    漪
    -0.07
    zan
    -0.07
    åĮª
    -0.07
    彬
    -0.07
    uyo
    -0.07
     Rue
    -0.07
     similarity
    -0.07
     NotImplemented
    -0.07
    禺
    -0.06
    çĽ¸ä¼¼åº¦
    -0.06
    POSITIVE LOGITS
    WithValue
    0.09
    åĪĨéħįçļĦ
    0.08
    วà¹Īาà¸ĩ
    0.08
     capacities
    0.08
     вмеÑģÑĤ
    0.08
    .capacity
    0.08
    è¿ĩåįĬ
    0.08
     vacancies
    0.08
    ommer
    0.07
     Annunci
    0.07
    Activations Density 0.002%

    No Known Activations