© 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. 12-TRANSCODER-HP
    7. 23647
    Prev
    Next
    INDEX
    Explanations

    Brit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anth
    -0.26
     nightmares
    -0.24
    rema
    -0.24
    åħĪ导
    -0.24
     hoped
    -0.24
     reached
    -0.24
    ismatic
    -0.24
    .lift
    -0.24
     McCart
    -0.23
    æĤ¬å¿µ
    -0.23
    POSITIVE LOGITS
    çªĿ
    0.29
    loon
    0.28
    ping
    0.25
    æĸĩåŃĹ
    0.25
    gain
    0.25
    fas
    0.24
    files
    0.24
    åİĨæŶ
    0.24
    ä¸ºçĽ®æłĩ
    0.24
     wings
    0.24
    Activations Density 0.290%

    No Known Activations