© 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. 16638
    Prev
    Next
    INDEX
    Explanations

    for characteristic or Tina

    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
    ìłľë¡ľ
    -0.08
    ÑģоÑĤ
    -0.07
    çģµåħ½
    -0.07
    .ip
    -0.07
    ulangan
    -0.07
    å¿ĥå®ī
    -0.07
    ×Ļר×ķת
    -0.07
    `=
    -0.07
    accio
    -0.07
    ä¸įåİĮ
    -0.07
    POSITIVE LOGITS
     outgoing
    0.08
    suming
    0.07
     Ausgang
    0.07
    utus
    0.07
    å¸ĥå±ĢåĴĮ
    0.07
    åĪĨè£Ĥ
    0.07
    æ´¾åĩº
    0.07
    缺å°ij
    0.07
    åĩºå¾ģ
    0.07
    aki
    0.07
    Activations Density 0.003%

    No Known Activations