© 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. 42683
    Prev
    Next
    INDEX
    Explanations

    given an array

    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
    rive
    -0.07
    ihal
    -0.07
    å¦ĤæĹł
    -0.07
    Ùħاء
    -0.06
    è¦ģä¹Īæĺ¯
    -0.06
     whichever
    -0.06
     govern
    -0.06
    ger
    -0.06
    çĦ¶å¤§
    -0.06
    å°ıçģ«
    -0.06
    POSITIVE LOGITS
    fds
    0.08
    å²±
    0.07
    ip
    0.07
    éĻIJæŶ
    0.07
    od
    0.07
    ipper
    0.07
    ebre
    0.07
    öd
    0.07
    olv
    0.07
    ató
    0.07
    Activations Density 0.026%

    No Known Activations