© 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. 38645
    Prev
    Next
    INDEX
    Explanations

    reach or propagate

    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
    ugn
    -0.08
    大麦
    -0.08
     bung
    -0.07
    صاد
    -0.07
    ç´§åĽºä»¶
    -0.07
    fang
    -0.07
    _serv
    -0.07
     Serv
    -0.07
    Serv
    -0.06
    urna
    -0.06
    POSITIVE LOGITS
    转移
    0.08
    å¾Ģåīį
    0.07
     propagate
    0.07
    çĤİçĤİ
    0.07
     AppState
    0.07
    -transfer
    0.07
    æŨ
    0.07
     reachable
    0.07
     propag
    0.07
     Reach
    0.07
    Activations Density 0.002%

    No Known Activations