© 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. 63867
    Prev
    Next
    INDEX
    Explanations

    range boundaries

    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
    genesis
    -0.08
    usher
    -0.08
    opa
    -0.08
    åľ¨è§Ħå®ļæŶéĹ´åĨħ
    -0.08
     Polisi
    -0.08
    catch
    -0.07
    opor
    -0.07
    inci
    -0.07
    bben
    -0.07
    æĭĽçĶŁç®Ģç«ł
    -0.07
    POSITIVE LOGITS
     range
    0.11
    èĮĥåĽ´åĨħ
    0.10
    -range
    0.10
    èĮĥåĽ´
    0.10
    range
    0.09
    ç¯Ħåľį
    0.09
    èĮĥåĽ´åĨħçļĦ
    0.09
     subrange
    0.08
    _range
    0.08
     Range
    0.08
    Activations Density 0.047%

    No Known Activations