© 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. 2957
    Prev
    Next
    INDEX
    Explanations

    length and measurement

    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
    agd
    -0.08
    转æŃ£
    -0.08
    wein
    -0.08
    ufe
    -0.08
    èİħ
    -0.08
    owers
    -0.08
     Kreis
    -0.08
    åľĪåľĪ
    -0.07
    icara
    -0.07
    å°Ķåħĭ
    -0.07
    POSITIVE LOGITS
    æµĭéĩı
    0.10
     measurement
    0.10
     Measurement
    0.10
     length
    0.09
    Measurement
    0.09
     measurements
    0.09
    éķ¿åº¦
    0.09
     measured
    0.09
     Length
    0.08
    æµĭéĩıçļĦ
    0.08
    Activations Density 0.003%

    No Known Activations