© 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. 55784
    Prev
    Next
    INDEX
    Explanations

    freedom of choice

    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
    rels
    -0.08
    udin
    -0.07
    åIJ»
    -0.07
    RIES
    -0.07
    اء
    -0.07
     diplom
    -0.07
    失èī²
    -0.06
    çľ¼åľĪ
    -0.06
    -webpack
    -0.06
    oon
    -0.06
    POSITIVE LOGITS
    èĩªä¸»
    0.11
    èĩªä¸»éĢīæĭ©
    0.11
     freedom
    0.10
    èĩªçĶ±çļĦ
    0.10
     autonomy
    0.10
    èĩªçĶ±
    0.10
    èĥ½åĬĽåıĬ
    0.10
    çļĦèĩªçĶ±
    0.09
     conscious
    0.09
     volunt
    0.09
    Activations Density 0.011%

    No Known Activations