© 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. 50009
    Prev
    Next
    INDEX
    Explanations

    intersecting points, junctions, intersections

    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
    çĶļèĩ³åľ¨
    -0.07
    åħ¶åIJį
    -0.06
    ä¼´
    -0.06
    çĶļèĩ³æľīäºĽ
    -0.06
    çĶļèĩ³æľī
    -0.06
     lyd
    -0.06
    çĨŁ
    -0.06
    achable
    -0.06
     usable
    -0.06
     even
    -0.06
    POSITIVE LOGITS
     intersect
    0.12
    交æ±ĩå¤Ħ
    0.12
     intersection
    0.12
     intersections
    0.12
    intersection
    0.11
     Intersection
    0.11
    交æ±ĩ
    0.11
    Intersection
    0.11
     intersects
    0.11
    _intersection
    0.10
    Activations Density 0.014%

    No Known Activations