© 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. 24168
    Prev
    Next
    INDEX
    Explanations

    and to investigate

    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
    atoria
    -0.09
    .viewport
    -0.09
    viso
    -0.08
    çī©è¯Ń
    -0.08
    äºĨä½łçļĦ
    -0.08
    igned
    -0.08
    keley
    -0.08
    å±ķå¼Ģåħ¨æĸĩ
    -0.08
    schau
    -0.08
    mia
    -0.08
    POSITIVE LOGITS
    åħ¼
    0.08
     zugleich
    0.07
    以åıĬ
    0.06
    º
    0.06
    ãģĬãĤĪãģ³
    0.06
    åıĬ
    0.06
    çŁ¥
    0.06
    åıĬ对
    0.06
    大山
    0.05
    compat
    0.05
    Activations Density 0.051%

    No Known Activations