© 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. 51615
    Prev
    Next
    INDEX
    Explanations

    omitted items, documents, name, received

    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
    åıªè¦ģèĥ½
    -0.09
    izm
    -0.08
    å·®ä¸įå¤ļäºĨ
    -0.07
    ÃģT
    -0.07
    ä¼ļæľīå¾Īå¤ļ
    -0.07
    æľªå¿ħ
    -0.07
     reinterpret
    -0.07
     ideally
    -0.07
     myriad
    -0.07
    uish
    -0.07
    POSITIVE LOGITS
    æĥħåĨµè¿Ľè¡ĮäºĨ
    0.08
    ä¸Ģåħ±
    0.07
    heb
    0.07
     sobr
    0.07
    åħ±è®¡
    0.07
    使çĶ¨æĥħåĨµ
    0.07
    è¿Ļæł·çļĦæĥħåĨµ
    0.07
    åħ±æľī
    0.07
     Masih
    0.07
     unanimously
    0.07
    Activations Density 0.016%

    No Known Activations