© 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. 7683
    Prev
    Next
    INDEX
    Explanations

    plans and goals

    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
     madrugada
    -0.07
     dét
    -0.07
    elat
    -0.07
     днем
    -0.06
    ahl
    -0.06
    ä¸Ń央纪å§Ķ
    -0.06
    æ·±å¤ľ
    -0.06
    Rép
    -0.06
    ãĥĪãĥ©ãĥĸãĥ«
    -0.06
    ä¸įæĩĤ
    -0.06
    POSITIVE LOGITS
     targets
    0.15
    缮æłĩ
    0.14
    缮æłĩçļĦ
    0.14
    缮æłĩåĴĮ
    0.14
     plans
    0.14
     ambitious
    0.14
    计åĪĴ
    0.13
    åıijå±ķ缮æłĩ
    0.13
     goals
    0.13
    计åĪĴçļĦ
    0.13
    Activations Density 0.148%

    No Known Activations