© 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. 2167
    Prev
    Next
    INDEX
    Explanations

    further

    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
    eno
    -0.07
    enet
    -0.07
    ÃŃv
    -0.06
    åħĪå°Ĩ
    -0.06
    äºĨä¸ĢåĪĩ
    -0.06
    uen
    -0.06
    akor
    -0.06
     compag
    -0.06
    <-
    -0.06
    åħĪåľ¨
    -0.06
    POSITIVE LOGITS
    ãģķãĤīãģ«
    0.09
    继ç»Ń
    0.09
    è¿Ľä¸ĢæŃ¥
    0.09
     ulteriore
    0.09
     weiteren
    0.08
     weiteres
    0.08
     further
    0.08
     weitere
    0.08
     weiter
    0.08
    åıĪ
    0.08
    Activations Density 0.057%

    No Known Activations