© 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. 19646
    Prev
    Next
    INDEX
    Explanations

    speed and velocity

    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
    chine
    -0.07
    omon
    -0.07
    iÅĤ
    -0.07
    æºIJ
    -0.07
    _MISSING
    -0.06
    iefert
    -0.06
    ä¸įæį¢
    -0.06
    emel
    -0.06
    طا
    -0.06
    pow
    -0.06
    POSITIVE LOGITS
    衬
    0.09
    รัà¸ģษà¹Į
    0.08
    ipay
    0.07
    Assignable
    0.07
    JSONObject
    0.07
     veloc
    0.07
    bsd
    0.07
    READY
    0.07
    å·´åĭĴ
    0.07
    _OBJ
    0.06
    Activations Density 0.004%

    No Known Activations