© 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. 10559
    Prev
    Next
    INDEX
    Explanations

    Let's say / a/an + noun

    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
    ç§įçļĦ
    -0.08
    éĢłçļĦ
    -0.07
    ç³»çļĦ
    -0.07
    éħĮæĥħ
    -0.07
    éħĮ
    -0.07
    æµ®äºij
    -0.06
    æĺ¯çľŁ
    -0.06
    wein
    -0.06
    _CLIP
    -0.06
     pinch
    -0.06
    POSITIVE LOGITS
    rig
    0.08
    idad
    0.07
     (~(
    0.07
     higien
    0.07
    iol
    0.07
    rogen
    0.07
    htub
    0.07
    æĹ¥çĶµ
    0.07
    νοÏį
    0.07
     condotto
    0.07
    Activations Density 0.001%

    No Known Activations