© 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. 2877
    Prev
    Next
    INDEX
    Explanations

    expressions with (x)

    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
    ì¶Ķ
    -0.08
    stadt
    -0.06
    ous
    -0.06
    çĪ±æĥľ
    -0.06
    é
    -0.06
    REQ
    -0.06
    oot
    -0.06
    sv
    -0.06
    o
    -0.06
    ype
    -0.06
    POSITIVE LOGITS
    amarin
    0.09
     Yön
    0.08
    cura
    0.08
    åıĬéħį件
    0.08
    ’all
    0.08
    'all
    0.08
    unos
    0.08
    olong
    0.08
    ycz
    0.08
    lotte
    0.08
    Activations Density 0.010%

    No Known Activations