© 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. 38883
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    Õ¡Õ£
    -0.08
    éº
    -0.07
    ças
    -0.07
    Dim
    -0.07
    ces
    -0.07
    /stream
    -0.07
    ceg
    -0.07
    baar
    -0.07
    ÃŃg
    -0.07
    å§ĭç»Īæĺ¯
    -0.07
    POSITIVE LOGITS
    apura
    0.08
    äºijå±±
    0.08
    æīĵæĪIJ
    0.07
    äºİå¿ĥ
    0.07
    å·³
    0.07
    å¸ĪåħĦ
    0.06
    两åı£
    0.06
    AndGet
    0.06
    icale
    0.06
    TRE
    0.06
    Activations Density 0.003%

    No Known Activations