© 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. 47983
    Prev
    Next
    INDEX
    Explanations

    pairing, polygons, string, 2

    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
    ÏĨο
    -0.07
    agnes
    -0.06
    е
    -0.06
    icc
    -0.06
    Safe
    -0.06
    akter
    -0.06
    lite
    -0.06
    çĶļèĢħ
    -0.06
    çĶµåŃIJç§ijæĬĢæľīéĻIJåħ¬åı¸
    -0.06
    обÑĢаз
    -0.06
    POSITIVE LOGITS
    zeni
    0.07
     Comer
    0.07
    çļĦä»ĸ
    0.07
    åı¤
    0.07
    æī¬éķ¿
    0.07
    peria
    0.06
    çīĻ齿
    0.06
    agin
    0.06
    awang
    0.06
    _pdu
    0.06
    Activations Density 0.005%

    No Known Activations