© 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. 21899
    Prev
    Next
    INDEX
    Explanations

    hexadecimal strings

    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
    ello
    -0.07
    izer
    -0.06
    ç¡ķæŀľ
    -0.06
    wall
    -0.06
    olog
    -0.06
    ÃŃlia
    -0.06
    wagon
    -0.06
    wt
    -0.06
    ï
    -0.06
    缸åħ³åĨħ容
    -0.06
    POSITIVE LOGITS
    OfSize
    0.08
    .NewReader
    0.08
    tuar
    0.08
     INTERRUPTION
    0.07
    CodeAt
    0.07
    inian
    0.07
    ivery
    0.07
    кладÑĭ
    0.07
    auft
    0.07
    atea
    0.07
    Activations Density 0.007%

    No Known Activations