© 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. 43360
    Prev
    Next
    INDEX
    Explanations

    form, Letter, ivalency, Atomic Scala

    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
    çīµ
    -0.09
    atis
    -0.07
    igl
    -0.07
    åħ¬åı¸åĨħéĥ¨
    -0.07
    åįİ强
    -0.07
    æľīåIJį
    -0.07
    大æĦı
    -0.07
    ëŁŃ
    -0.06
    TERN
    -0.06
    resso
    -0.06
    POSITIVE LOGITS
    ordo
    0.08
    Õ¸ÖĤÕ¶
    0.08
    ÙĬÙģا
    0.07
    次
    0.07
    ìa
    0.07
     Unsure
    0.07
    AndUpdate
    0.06
    ünd
    0.06
    elseif
    0.06
     minori
    0.06
    Activations Density 0.001%

    No Known Activations