© 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. 2349
    Prev
    Next
    INDEX
    Explanations

    distance and propagation paths

    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
     Seben
    -0.07
    atters
    -0.06
    IDA
    -0.06
    acy
    -0.06
    ubah
    -0.06
     riserva
    -0.06
    çĶļèĩ³åľ¨
    -0.06
    çĥĪçģ«
    -0.06
    tero
    -0.06
    大山
    -0.06
    POSITIVE LOGITS
    distance
    0.11
     distance
    0.10
    è·Ŀ离
    0.10
    çļĦè·Ŀ离
    0.10
    è·ĿéĽ¢
    0.10
     distances
    0.10
    -distance
    0.09
    Distance
    0.08
     Distance
    0.08
    rij
    0.08
    Activations Density 0.001%

    No Known Activations