© 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. 8727
    Prev
    Next
    INDEX
    Explanations

    extracted data

    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
    CELER
    -0.27
     Influ
    -0.27
    imentary
    -0.26
     influences
    -0.25
     Influence
    -0.25
    rush
    -0.23
    ByUrl
    -0.23
    secs
    -0.23
     Investigations
    -0.23
    ams
    -0.23
    POSITIVE LOGITS
    partial
    0.29
     .č↵
    0.27
    .č↵
    0.25
    ---↵
    0.25
    éĤ£æĺ¯
    0.25
     among
    0.24
    `.↵
    0.24
     amongst
    0.24
    Partial
    0.24
    æľīæľºä¼ļ
    0.23
    Activations Density 0.060%

    No Known Activations