© 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. 16066
    Prev
    Next
    INDEX
    Explanations

    line breaks or newline characters in technical documentation and structured text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    ients
    -0.09
    ibri
    -0.08
    tsky
    -0.08
    łí
    -0.07
    inders
    -0.07
    ique
    -0.07
    иден
    -0.07
    inery
    -0.07
    à°²
    -0.07
    igura
    -0.07
    POSITIVE LOGITS
    üst
    0.06
     deliberately
    0.06
    çķij
    0.06
    ayer
    0.06
    缴è¾ĸå¸Ĥ
    0.06
    beh
    0.06
    åħ¬åı·
    0.06
    常说
    0.06
    jax
    0.06
    ä½ľäºĨ
    0.06
    Activations Density 0.000%

    No Known Activations