© 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. 56121
    Prev
    Next
    INDEX
    Explanations

    predator or predation

    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
     defiant
    -0.08
    å¹ħ
    -0.07
    _PARAMS
    -0.07
    cules
    -0.07
    arness
    -0.07
    åĢĶ
    -0.07
    .generator
    -0.07
    ptos
    -0.07
    èĥ¶
    -0.07
    è¿IJè¡Į
    -0.07
    POSITIVE LOGITS
    ruck
    0.08
     mortality
    0.08
    åĩºæ²¡
    0.07
    æĹłå¤Ħä¸įåľ¨
    0.07
    被æįķ
    0.07
    åħī顾
    0.07
    æĭ¦æĪª
    0.07
     predator
    0.07
     populations
    0.07
     predators
    0.07
    Activations Density 0.021%

    No Known Activations