© 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. 47105
    Prev
    Next
    INDEX
    Explanations

    forced, compulsory, mandatory

    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
     délég
    -0.08
    _multiplier
    -0.08
    owski
    -0.08
    ameni
    -0.08
    аниÑĨ
    -0.08
    OPP
    -0.08
    æĨ§
    -0.07
    rome
    -0.07
    tent
    -0.07
     gesta
    -0.07
    POSITIVE LOGITS
    强åĪ¶
    0.17
     forced
    0.15
    强åĪ¶æĢ§
    0.15
    å¼·åĪ¶
    0.15
     compulsory
    0.14
     mandatory
    0.14
    forced
    0.14
    æĮĩå®ļçļĦ
    0.14
    被迫
    0.13
    mandatory
    0.13
    Activations Density 0.229%

    No Known Activations