© 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. 64668
    Prev
    Next
    INDEX
    Explanations

    investigates, address, help

    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
    èĤ´
    -0.07
    èĤ²
    -0.07
    awns
    -0.07
    åĿł
    -0.07
    å½Ŀ
    -0.06
    viously
    -0.06
     prez
    -0.06
    ahr
    -0.06
     certainly
    -0.06
    çĽ
    -0.06
    POSITIVE LOGITS
    åħ¶å®ĥçļĦ
    0.07
    çļĦåħ¶ä»ĸ
    0.07
    uye
    0.07
    å¾ľ
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    åľ¨åħ¶ä»ĸ
    0.07
     practical
    0.07
    -other
    0.07
     {}:
    0.07
    igu
    0.07
    Activations Density 0.001%

    No Known Activations