© 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. 39114
    Prev
    Next
    INDEX
    Explanations

    immutable strings

    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
    Repeat
    -0.08
    ä¹ĭæĢ¥
    -0.08
    çIJ¥
    -0.08
    ä¸ĭ线
    -0.08
    inga
    -0.08
    örer
    -0.08
    .must
    -0.07
    _defaults
    -0.07
    设计è§ĦèĮĥ
    -0.07
    ä¾ĽéĶĢ
    -0.07
    POSITIVE LOGITS
     unlimited
    0.10
     limitless
    0.08
     Unlimited
    0.08
    .BigInteger
    0.08
     indefinitely
    0.07
     rem
    0.07
     beyond
    0.07
    -native
    0.07
    è¶ħè¶Ĭ
    0.06
    èĩ
    0.06
    Activations Density 0.006%

    No Known Activations