© 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. 47475
    Prev
    Next
    INDEX
    Explanations

    define name

    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
     Tew
    -0.08
    doll
    -0.07
    enzen
    -0.07
    åīį车
    -0.07
    omot
    -0.07
    okin
    -0.07
    åĽŃåĨħ
    -0.07
    otte
    -0.07
    fri
    -0.07
    ismet
    -0.06
    POSITIVE LOGITS
    ancer
    0.07
    çŁ³åĪ»
    0.07
    reon
    0.07
    çIJ¢
    0.07
    reno
    0.07
    ench
    0.06
    移
    0.06
    éĩĩ
    0.06
    .persist
    0.06
    orter
    0.06
    Activations Density 0.001%

    No Known Activations