© 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. 27-TRANSCODER-HP
    7. 57357
    Prev
    Next
    INDEX
    Explanations

    seasons or time periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smooth
    -0.53
    å¹³éĿĻ
    -0.52
     Smooth
    -0.50
    smooth
    -0.48
     smoother
    -0.47
    Smooth
    -0.47
    å¹³åĿ¦
    -0.47
    åħīæ»ij
    -0.47
    平稳
    -0.47
     smoothed
    -0.41
    POSITIVE LOGITS
     mas
    0.27
    itals
    0.26
    ÑĥменÑĤ
    0.26
    endencies
    0.26
    æĦŁåħ´è¶£
    0.25
    ativ
    0.24
     disposed
    0.23
    mq
    0.23
     SG
    0.23
    ä¸İæŶ
    0.23
    Activations Density 0.008%

    No Known Activations