© 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. 16632
    Prev
    Next
    INDEX
    Explanations

    "what" followed by "my" or "I"

    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
    uncul
    -0.09
    æŶæį·
    -0.09
    ocu
    -0.08
    izm
    -0.08
    "crypto
    -0.08
    \Message
    -0.08
    çģ¿
    -0.08
    ä¹ĿéľĦ
    -0.08
    _RSP
    -0.08
    trz
    -0.08
    POSITIVE LOGITS
    E
    0.06
     pratic
    0.06
    èĩ´
    0.06
    eho
    0.06
    sver
    0.06
     code
    0.06
    _wrong
    0.06
    insky
    0.06
    Code
    0.06
    èĦļæľ¬
    0.06
    Activations Density 0.004%

    No Known Activations