© 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. 17782
    Prev
    Next
    INDEX
    Explanations

    injecting or injections

    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
    agher
    -0.09
    pton
    -0.08
    جد
    -0.08
    wic
    -0.08
    ì¦Ī
    -0.08
    housing
    -0.08
    fare
    -0.08
    isans
    -0.08
    ington
    -0.08
    èºĩ
    -0.08
    POSITIVE LOGITS
    ive
    0.08
    ivity
    0.08
     nhầm
    0.08
    ividual
    0.08
    aneous
    0.08
    oglob
    0.08
    çļĦéĥ½æĺ¯
    0.08
    BaseContext
    0.07
    ary
    0.07
    ively
    0.07
    Activations Density 0.047%

    No Known Activations