© 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. 15558
    Prev
    Next
    INDEX
    Explanations

    each followed by describing words

    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
    ety
    -0.07
    çIJIJ
    -0.07
    æīĢä»¥åľ¨
    -0.07
    ç¼ĺæķħ
    -0.07
    躲
    -0.06
    å¨ħ
    -0.06
    ijľ
    -0.06
    СÐŀ
    -0.06
    ef
    -0.06
    анда
    -0.06
    POSITIVE LOGITS
    rlen
    0.09
     therein
    0.08
    è¦ģä¹Ī
    0.07
    纳æĸ¯
    0.07
     darin
    0.07
    -NLS
    0.07
    éĨį
    0.07
     enten
    0.07
    è¦ģä¹Īæĺ¯
    0.07
    ROL
    0.07
    Activations Density 0.013%

    No Known Activations