© 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. 62091
    Prev
    Next
    INDEX
    Explanations

    placeholders like ##TheId##, {0}

    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
    _ARB
    -0.08
    ãĤĵãģ©
    -0.07
    ocz
    -0.07
    çķij
    -0.07
     dicapai
    -0.07
    llum
    -0.07
    stieg
    -0.07
     dicts
    -0.07
    åħĥèµ·
    -0.07
     optionally
    -0.07
    POSITIVE LOGITS
    éĨ
    0.08
    亲
    0.07
    åµĮåħ¥
    0.07
    kä
    0.07
    medi
    0.07
    à¹ĥà¸Ļà¸ģารà¸Ĺำ
    0.06
    entino
    0.06
    ä»ĭåħ¥
    0.06
    maz
    0.06
    ogu
    0.06
    Activations Density 0.028%

    No Known Activations