© 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. 17124
    Prev
    Next
    INDEX
    Explanations

    radius

    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
    infeld
    -0.08
    tott
    -0.07
     Fields
    -0.07
     darling
    -0.07
    æµģåĪ©
    -0.07
     INLINE
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    Ø´ÙĤ
    -0.07
    Acceler
    -0.07
    aben
    -0.07
    POSITIVE LOGITS
    åįĬå¾Ħ
    0.10
    (radius
    0.10
     Radius
    0.09
     radius
    0.09
    _radius
    0.09
    .radius
    0.09
    Radius
    0.09
    _RADIUS
    0.09
    radius
    0.08
     enc
    0.08
    Activations Density 0.011%

    No Known Activations