© 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. 56452
    Prev
    Next
    INDEX
    Explanations

    positive values, continuous, LinearLayout

    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
    veau
    -0.08
    .Excel
    -0.08
     ủi
    -0.08
    çĽ¸å¯¹è¾ĥé«ĺ
    -0.08
    licken
    -0.08
    mund
    -0.08
    roda
    -0.08
    kland
    -0.08
    ¾¸
    -0.08
    ivit
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    士
    0.06
    oral
    0.06
    æµ·
    0.06
    earable
    0.06
    elh
    0.06
     acaso
    0.05
     Ragnar
    0.05
    uru
    0.05
    åIJī祥
    0.05
    Activations Density 0.011%

    No Known Activations