© 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. 20218
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
    endorf
    -0.07
    رÙĪÙĬ
    -0.07
    yani
    -0.07
    ãĥŃãĥŀ
    -0.06
    åIJĽ
    -0.06
    NV
    -0.06
    Rest
    -0.06
     Ville
    -0.06
    igura
    -0.06
     Dow
    -0.06
    POSITIVE LOGITS
    以身
    0.08
    ause
    0.08
    çijŀæĭī
    0.08
    è¦ģ强
    0.08
    tober
    0.07
    ------------------------------------------------------------------------------------------------
    0.07
    饵
    0.07
    iously
    0.07
    ugh
    0.07
    çĶŁæºIJ
    0.07
    Activations Density 0.009%

    No Known Activations