© 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. 7770
    Prev
    Next
    INDEX
    Explanations

    giving or providing something

    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
    ibar
    -0.08
    etty
    -0.08
    etr
    -0.08
    umbo
    -0.08
    èĥ½æľī
    -0.07
     пÑĢиÑģÑĥ
    -0.07
    trak
    -0.07
    æīĢ产çĶŁçļĦ
    -0.07
     Matte
    -0.07
    hipster
    -0.07
    POSITIVE LOGITS
    äºĨä¸Ģç³»åĪĹ
    0.08
    çļĦæĺ¯ä¸Ģ个
    0.07
    åĪ°çļĦ
    0.07
    ëIJľ
    0.07
    s
    0.07
    sample
    0.07
    vised
    0.07
    äºĨä¸ĢäºĽ
    0.07
    Ïĥαν
    0.07
     sample
    0.06
    Activations Density 0.016%

    No Known Activations