© 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. 44082
    Prev
    Next
    INDEX
    Explanations

    function $f:\mathbb{R}\to\mathbb{R}$

    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
    lán
    -0.08
    leos
    -0.08
    obie
    -0.08
    ocked
    -0.08
    lant
    -0.08
    ак
    -0.08
    æĸĩæѦ
    -0.08
    anies
    -0.07
    å¤©æ±ł
    -0.07
    igner
    -0.07
    POSITIVE LOGITS
    bron
    0.07
    æĥ¹
    0.06
    ведениÑİ
    0.06
    zey
    0.06
    æ¼Ĩ
    0.05
     inputs
    0.05
    éĹ¹
    0.05
    ulli
    0.05
    çĶµä¿¡
    0.05
    çĿ
    0.05
    Activations Density 0.008%

    No Known Activations