© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14154
    Prev
    Next
    INDEX
    Explanations

    typeof checks

    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
    adini
    -0.09
    onser
    -0.09
    uco
    -0.08
    éģĵéģĵ
    -0.08
    usura
    -0.08
    usak
    -0.08
    ¿IJ
    -0.08
    ahui
    -0.08
    rab
    -0.08
    缸åħ³æĥħåĨµ
    -0.08
    POSITIVE LOGITS
    (s
    0.07
    为æķ°
    0.07
    ity
    0.06
     fel
    0.06
    (
    0.05
     uninitialized
    0.05
    åĸľ
    0.05
    æķ°çĻ¾ä¸ĩ
    0.05
     nest
    0.05
    ect
    0.05
    Activations Density 0.024%

    No Known Activations