© 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. 29394
    Prev
    Next
    INDEX
    Explanations

    relation between mass and weight

    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
    éģĩ
    -0.09
    gis
    -0.08
    εδ
    -0.07
     ressort
    -0.07
    æľŁæ»¡
    -0.07
    inos
    -0.07
    ÙĨز
    -0.07
    åħįè´¹ä¸ĭè½½
    -0.07
    éģĵéģĵ
    -0.07
    hlen
    -0.07
    POSITIVE LOGITS
    çŁ¥åħ¶
    0.08
    èĬ
    0.08
    Controls
    0.08
     correlate
    0.07
     correl
    0.07
    åĭ¾
    0.07
    åıĺéĩı
    0.07
     Controls
    0.07
    åĨ³å®ļ
    0.07
     correlation
    0.07
    Activations Density 0.052%

    No Known Activations