© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20687
    Prev
    Next
    INDEX
    Explanations

    overflow

    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
    lagt
    -0.09
    ÙĪÙĤÙĬ
    -0.09
    ricia
    -0.09
    ynchronously
    -0.08
    ouver
    -0.08
    ×ķר×Ķ
    -0.08
    ovah
    -0.08
    åħ°è¾¾
    -0.08
     STDERR
    -0.08
    ลฯ
    -0.08
    POSITIVE LOGITS
    ingly
    0.09
    ion
    0.08
    ed
    0.08
    Ùĩ
    0.07
    es
    0.07
    orno
    0.07
    溢
    0.07
    ers
    0.07
    åĽ
    0.07
    abe
    0.07
    Activations Density 0.012%

    No Known Activations