© 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. 8894
    Prev
    Next
    INDEX
    Explanations

    road or roads

    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
     باÙĦÙĦÙĩ
    -0.08
    oleon
    -0.08
    ä¸įæķ£
    -0.08
    ç§ijåijĺ
    -0.07
    ersions
    -0.07
    irk
    -0.07
    AtPath
    -0.07
     Kapal
    -0.07
    quilib
    -0.07
    Ĺ
    -0.07
    POSITIVE LOGITS
    iness
    0.10
    ä¸ĬçļĦ
    0.10
    -going
    0.09
    两æĹģ
    0.09
    ways
    0.09
    θεν
    0.08
    INESS
    0.08
     pandang
    0.08
    bags
    0.08
    -facing
    0.08
    Activations Density 0.067%

    No Known Activations