© 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. 40441
    Prev
    Next
    INDEX
    Explanations

    ban, prohibition, forbid

    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
    quires
    -0.10
    ergestellt
    -0.09
    heber
    -0.08
    åºĦéķĩ
    -0.08
    оÑĤе
    -0.08
    ë§ģ
    -0.08
    aland
    -0.08
     behalf
    -0.08
    gnore
    -0.08
    -même
    -0.08
    POSITIVE LOGITS
    ä¸į严
    0.09
    äºĭéłħ
    0.09
    ä¸įä½ıçļĦ
    0.08
    listed
    0.08
     Äijoán
    0.08
    ìĤ¬íķŃ
    0.08
     adanya
    0.08
    à¹Ħมà¹Īà¹ĥหà¹ī
    0.08
    ä¹ĭåĪĹ
    0.08
    äºĨä¸ĢåĪĩ
    0.07
    Activations Density 0.025%

    No Known Activations