© 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. 31964
    Prev
    Next
    INDEX
    Explanations

    bond strength, length, type

    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
    teen
    -0.09
    heen
    -0.08
    ammans
    -0.08
    ounder
    -0.08
    ound
    -0.08
    odore
    -0.08
    istrator
    -0.08
    wards
    -0.08
    -vous
    -0.08
    ksen
    -0.08
    POSITIVE LOGITS
    sWith
    0.09
    less
    0.08
    (s
    0.08
    ier
    0.07
    line
    0.07
    aries
    0.07
    çĿĢçļĦ
    0.07
    ings
    0.07
    urant
    0.07
    és
    0.07
    Activations Density 0.011%

    No Known Activations