© 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. 46689
    Prev
    Next
    INDEX
    Explanations

    argument/premise

    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
    erci
    -0.08
    èµ·æºIJäºİ
    -0.07
    หัส
    -0.07
     hingegen
    -0.07
    ciso
    -0.07
     неоÑĤ
    -0.07
     Roos
    -0.07
    管çIJĨè§ĦèĮĥ
    -0.07
    apun
    -0.07
     denuncia
    -0.07
    POSITIVE LOGITS
     premise
    0.10
     implicitly
    0.09
     Prem
    0.08
     premises
    0.08
    Prem
    0.08
    éĢ»è¾ij
    0.08
    éļIJåIJ«
    0.08
     presup
    0.08
    åīįæıIJ
    0.08
     intended
    0.08
    Activations Density 0.003%

    No Known Activations