© 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. 18467
    Prev
    Next
    INDEX
    Explanations

    loops and iteration structures

    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
     misd
    -0.07
    »;
    -0.07
    eball
    -0.06
     poda
    -0.06
     Fourth
    -0.06
    Mailer
    -0.06
    yman
    -0.06
    ucci
    -0.06
    mtime
    -0.06
     Couples
    -0.06
    POSITIVE LOGITS
    agn
    0.07
    èµı
    0.07
    以åħ¶
    0.07
    ловиÑĩ
    0.07
     devoted
    0.07
    olia
    0.07
    è¨Ģ
    0.07
    bras
    0.07
    åħ¶æŀĹ
    0.06
    heden
    0.06
    Activations Density 0.006%

    No Known Activations