© 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. 42978
    Prev
    Next
    INDEX
    Explanations

    HOBr, ADP, or ACE

    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
    èĩªè´Ł
    -0.06
     hered
    -0.06
     Amb
    -0.06
    .Escape
    -0.06
    误工
    -0.06
    ospace
    -0.06
    okra
    -0.06
    bios
    -0.06
     nip
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
    å®ŀå¤Ħ
    0.08
    едÑĥ
    0.08
    år
    0.07
    ahal
    0.07
    -decoration
    0.07
    elts
    0.07
    unami
    0.07
    æ®ĸ
    0.07
    ä»Ģä¹Īåij¢
    0.07
    ães
    0.07
    Activations Density 0.004%

    No Known Activations