© 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. 23-TRANSCODER-HP
    7. 24317
    Prev
    Next
    INDEX
    Explanations

    Parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨éĤ£éĩĮ
    -0.26
    ãģĵãģĿ
    -0.26
     favor
    -0.26
    edor
    -0.25
    .MM
    -0.25
    åģľå·¥
    -0.24
     pile
    -0.24
    .IsMatch
    -0.24
     cambio
    -0.23
    ering
    -0.23
    POSITIVE LOGITS
    alan
    0.30
    Website
    0.28
    ienia
    0.27
     Website
    0.27
    inkle
    0.27
    âĹĢ
    0.26
    ioc
    0.26
     wik
    0.25
    Nich
    0.25
    _website
    0.25
    Activations Density 0.002%

    No Known Activations