© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25120
    Prev
    Next
    INDEX
    Explanations

    distance units and directions

    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
    apie
    -0.07
    æµģåħ¥
    -0.07
    جاÙħ
    -0.07
    alik
    -0.07
    ucker
    -0.06
    DECL
    -0.06
    åĪĨéħįåĪ°
    -0.06
    plit
    -0.06
    æĤĶ
    -0.06
    ied
    -0.06
    POSITIVE LOGITS
    è·Ŀ离
    0.12
     distance
    0.12
    è·ĿéĽ¢
    0.11
    distance
    0.10
    车ç¨ĭ
    0.10
     Distance
    0.10
    Distance
    0.10
    çļĦè·Ŀ离
    0.10
     distances
    0.10
     distanza
    0.10
    Activations Density 0.098%

    No Known Activations