© 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. 56901
    Prev
    Next
    INDEX
    Explanations

    problem and description

    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
    å°ıå¿ĥ
    -0.08
    iates
    -0.07
    å¾Ĺæīĭ
    -0.07
    obo
    -0.07
    steen
    -0.07
     Bryce
    -0.07
    该åIJį
    -0.07
    Ñīенко
    -0.07
    ugins
    -0.07
    IDES
    -0.07
    POSITIVE LOGITS
    /problem
    0.10
     problem
    0.10
    éĹ®é¢ĺæĺ¯
    0.09
    problem
    0.09
     Problem
    0.09
    çļĦ主è¦ģéĹ®é¢ĺ
    0.09
     problema
    0.08
    ä»Ģä¹ĪéĹ®é¢ĺ
    0.08
    åħ·ä½ĵéĹ®é¢ĺ
    0.08
     пÑĢоблемÑĥ
    0.08
    Activations Density 0.258%

    No Known Activations