© 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. 40874
    Prev
    Next
    INDEX
    Explanations

    planet or planetary contexts

    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
    s
    -0.09
    mals
    -0.08
    erk
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    åħ°å¾·
    -0.08
    ات
    -0.07
    çĻ½æ²Ļ
    -0.07
    pek
    -0.07
    oss
    -0.07
    sdale
    -0.07
    POSITIVE LOGITS
    esimal
    0.14
    wide
    0.10
    arium
    0.10
    ially
    0.10
    ceau
    0.09
    asma
    0.09
    iable
    0.09
    à§Ģয়
    0.09
     entière
    0.08
    shine
    0.08
    Activations Density 0.008%

    No Known Activations