© 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. 57218
    Prev
    Next
    INDEX
    Explanations

    cardinal 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
    å¤į
    -0.07
     Coll
    -0.06
    nest
    -0.06
    åıįå¤į
    -0.06
    enses
    -0.06
    ä¸įéĢĤ
    -0.06
    miss
    -0.06
    å¤ļ次
    -0.06
    å¾Ģ
    -0.06
    åŃIJåľ¨
    -0.06
    POSITIVE LOGITS
    èĢĮèµ°
    0.09
    orius
    0.08
     Cursors
    0.08
    Truthy
    0.08
     downstream
    0.08
     spok
    0.08
    øs
    0.08
    aight
    0.08
    figcaption
    0.08
    oci
    0.08
    Activations Density 0.050%

    No Known Activations