© 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. 55345
    Prev
    Next
    INDEX
    Explanations

    arrival and location

    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
    ç§ī
    -0.08
    Ùĥات
    -0.07
     arises
    -0.07
     moves
    -0.07
     arise
    -0.07
     moved
    -0.07
    Moves
    -0.06
    èµ°çļĦ
    -0.06
    Prototype
    -0.06
    ä¸Ĭè¡Ĺ
    -0.06
    POSITIVE LOGITS
     angekommen
    0.14
    åĪ°è¾¾
    0.11
    缮çļĦåľ°
    0.11
     ëıĦì°©
    0.10
    æĬµè¾¾
    0.10
     arrival
    0.10
    èIJ½åľ°
    0.10
    åĪ°éģĶ
    0.10
    arrival
    0.10
     destinazione
    0.10
    Activations Density 0.148%

    No Known Activations