© 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. 3104
    Prev
    Next
    INDEX
    Explanations

    preposition, then specific word

    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
    0
    -0.06
    èĢĮéĤ£äºĽ
    -0.06
    -0.06
    1
    -0.06
    X
    -0.06
    åı²
    -0.06
    enders
    -0.05
     history
    -0.05
     O
    -0.05
    åı²çļĦ
    -0.05
    POSITIVE LOGITS
    å°Ķæĸ¯
    0.10
    ÑĢово
    0.09
    ÑģÑĤÑĢе
    0.09
    ndata
    0.09
    ãĤ¡
    0.08
     Valu
    0.08
    oldem
    0.08
    çī¹å°Ķ
    0.08
    -wall
    0.08
    igné
    0.08
    Activations Density 0.578%

    No Known Activations