© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    chemotaxis, phototropism, attractant

    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
    oga
    -0.07
    åİĭåĪ¶
    -0.07
    åīĬ
    -0.07
    çĽijä¼ļ
    -0.07
    é¢IJ
    -0.07
    æľªç»ıæİĪæĿĥ
    -0.07
    ä½ĻçĥŃ
    -0.06
    æ¶ĪåĮĸçļĦ
    -0.06
     Regular
    -0.06
    occo
    -0.06
    POSITIVE LOGITS
     directional
    0.11
     attraction
    0.10
    è¶ĭ
    0.10
    å®ļåIJij
    0.10
     attractiveness
    0.09
    缮çļĦåľ°
    0.09
     directing
    0.09
    è¿ģ移
    0.09
     attracting
    0.09
    à¸Ĺิศà¸Ĺาà¸ĩ
    0.09
    Activations Density 0.075%

    No Known Activations