© 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. 42770
    Prev
    Next
    INDEX
    Explanations

    threshold value or voltage

    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
     halnya
    -0.09
    è´¸
    -0.08
    kaar
    -0.08
    otin
    -0.08
    OrUpdate
    -0.07
    éron
    -0.07
    alborg
    -0.07
    åı²çļĦ
    -0.07
    heu
    -0.07
    oto
    -0.07
    POSITIVE LOGITS
    reshold
    0.11
    ed
    0.09
    ing
    0.09
    less
    0.08
    ers
    0.08
    inkle
    0.08
    bard
    0.08
    éĻĦè¿ij
    0.08
    iram
    0.07
    æĢ§çļĦ
    0.07
    Activations Density 0.016%

    No Known Activations