© 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. 46160
    Prev
    Next
    INDEX
    Explanations

    ideal futures and dreams

    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
    umenta
    -0.08
    alls
    -0.08
    etts
    -0.08
     zada
    -0.08
    ä¸įåı¯å¿½è§Ĩ
    -0.08
    üb
    -0.08
    stairs
    -0.07
    æķıæĦŁçļĦ
    -0.07
    -important
    -0.07
    ç»ķåŁİ
    -0.07
    POSITIVE LOGITS
    çIJĨæĥ³
    0.14
     ideal
    0.13
    ideal
    0.12
     envisioned
    0.11
    çļĦçIJĨæĥ³
    0.11
    æŀĦæĥ³
    0.11
    çIJĨæĥ³çļĦ
    0.11
     ideals
    0.11
    设æĥ³
    0.11
    Ideal
    0.10
    Activations Density 0.101%

    No Known Activations