© 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. 43902
    Prev
    Next
    INDEX
    Explanations

    facing issue

    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
     vaguely
    -0.07
    ulp
    -0.07
     pire
    -0.07
    ва
    -0.06
    ich
    -0.06
    osz
    -0.06
    çīĮ
    -0.06
     restricted
    -0.06
    imal
    -0.06
    ä¸ĢåIJ¬
    -0.06
    POSITIVE LOGITS
    weg
    0.08
    obel
    0.08
    gica
    0.08
    å¾ĹçĽĬ
    0.08
    确信
    0.08
    edur
    0.08
    มัà¹Īà¸Ļà¹ĥà¸Ī
    0.08
     conclus
    0.08
     ÑĥвеÑĢенноÑģÑĤÑĮ
    0.08
    没æľīéĹ®é¢ĺ
    0.07
    Activations Density 0.018%

    No Known Activations