© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32224
    Prev
    Next
    INDEX
    Explanations

    direction and sign

    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
    ä¹ĭ乡
    -0.08
     Constit
    -0.07
     master
    -0.07
    master
    -0.07
     constit
    -0.07
    -master
    -0.07
    çħĻ
    -0.07
     MASTER
    -0.07
     masters
    -0.07
    è§Ħæł¼çļĦ
    -0.07
    POSITIVE LOGITS
     polarity
    0.10
    缸åıįçļĦ
    0.09
     direction
    0.09
     signs
    0.09
     sign
    0.08
    缸åıį
    0.08
    direction
    0.08
    -signed
    0.08
    æĸ¹åIJij
    0.08
     positive
    0.08
    Activations Density 0.014%

    No Known Activations