© 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. 11726
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    é¡¿äºĨé¡¿
    -0.07
    ()
    -0.06
    æ±
    -0.06
    iho
    -0.06
    对åºĶ
    -0.06
    eus
    -0.06
    [],
    -0.06
    S
    -0.06
    entin
    -0.06
    Ä©
    -0.06
    POSITIVE LOGITS
    缨
    0.08
     Ðijожи
    0.08
    å°¼æĸ¯
    0.07
    -mon
    0.07
    laise
    0.07
    blend
    0.07
    _MR
    0.07
    baden
    0.07
    åıªçĶ¨
    0.07
     Ensemble
    0.07
    Activations Density 0.104%

    No Known Activations