© 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. 17799
    Prev
    Next
    INDEX
    Explanations

    distance or 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
    argas
    -0.08
    fach
    -0.08
    åĪĨéħįçļĦ
    -0.07
     jad
    -0.07
    istros
    -0.07
    åĪĨéħį
    -0.07
    zaak
    -0.07
     목
    -0.07
    è«
    -0.07
    icura
    -0.07
    POSITIVE LOGITS
    åįĬå¾Ħ
    0.12
     radius
    0.11
    Radius
    0.10
     Radius
    0.10
    _radius
    0.10
    .radius
    0.10
    -radius
    0.09
     centered
    0.09
    adius
    0.09
     surrounding
    0.09
    Activations Density 0.035%

    No Known Activations