© 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. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107346
    Prev
    Next
    INDEX
    Explanations

    units of time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иÑħ
    -0.27
    æĪIJçĨŁ
    -0.27
    èĢħ
    -0.27
    ts
    -0.26
    èĢħçļĦ
    -0.25
    åģĩ
    -0.25
    mt
    -0.24
    åįģ大
    -0.24
    说
    -0.24
     Chow
    -0.24
    POSITIVE LOGITS
     years
    0.45
    ä¸Ģ段æŶéĹ´
    0.44
     weeks
    0.43
     months
    0.42
    两年
    0.40
    åįĬ个æľĪ
    0.40
    åĩłå¹´
    0.39
     hours
    0.39
     periods
    0.38
     centuries
    0.38
    Activations Density 1.516%

    No Known Activations