© 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. 30577
    Prev
    Next
    INDEX
    Explanations

    management, Excel file, friendly

    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
    brids
    -0.08
    èĤĮçĺ¤
    -0.07
    irit
    -0.07
    ]."
    -0.07
    '].
    -0.07
    ]].
    -0.07
    bia
    -0.07
     weiterlesen
    -0.07
    imately
    -0.07
    vez
    -0.07
    POSITIVE LOGITS
    s
    0.08
    hell
    0.07
    ney
    0.07
    unk
    0.07
    sic
    0.07
     vs
    0.06
    æľĪåŃIJ
    0.06
    寮
    0.06
    饿
    0.06
    resp
    0.06
    Activations Density 0.002%

    No Known Activations