© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    minimal, limited, few

    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
    ä½Ĩæĺ¯æ²¡æľī
    -0.07
    enges
    -0.07
    geg
    -0.07
    毫ä¸į
    -0.07
    ieste
    -0.07
    rane
    -0.07
     tutte
    -0.06
     вÑģеÑħ
    -0.06
    neau
    -0.06
     вÑģеми
    -0.06
    POSITIVE LOGITS
    å¾Īå°ij
    0.16
    çĶļå°ij
    0.15
    æŀģå°ij
    0.14
    è¾ĥå°ij
    0.14
    å¾Īå°ijæľī
    0.12
     hardly
    0.11
     few
    0.11
    ãģĹãģĭ
    0.11
    Few
    0.10
     minimal
    0.10
    Activations Density 0.280%

    No Known Activations