© 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. 61697
    Prev
    Next
    INDEX
    Explanations

    to encounter problems

    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
    istration
    -0.09
    isters
    -0.08
    atory
    -0.08
    gow
    -0.08
    quam
    -0.08
    åħ¶äºĭ
    -0.07
    gone
    -0.07
    itorios
    -0.07
    ÑĥÑĢг
    -0.07
    तà¥įव
    -0.07
    POSITIVE LOGITS
     gỡ
    0.12
    OrCreate
    0.10
    åĴĮå¤ĦçIJĨ
    0.09
    åĪ°çļĦ
    0.09
    enner
    0.08
    /use
    0.08
     nhau
    0.08
     encountered
    0.08
    IgnoreCase
    0.07
    anche
    0.07
    Activations Density 0.053%

    No Known Activations