© 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. 40999
    Prev
    Next
    INDEX
    Explanations

    concentration, limit, level, cap, age

    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
    ese
    -0.08
    ÙĩÙĦ
    -0.07
    miot
    -0.07
    èį¤
    -0.06
    pone
    -0.06
    .community
    -0.06
    çĿ¦
    -0.06
     Wilde
    -0.06
    é¢IJ
    -0.06
    _repeat
    -0.06
    POSITIVE LOGITS
     allowed
    0.09
    é»ĺ认
    0.08
    åı¯ä»¥èĩªçĶ±
    0.08
    åı¯éļıæŶ
    0.08
    åı¯ä»¥åIJĮæŶ
    0.08
     ((__
    0.08
     default
    0.08
    cuit
    0.08
     easily
    0.08
    abila
    0.08
    Activations Density 0.311%

    No Known Activations