© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161628
    Prev
    Next
    INDEX
    Explanations

    knight

    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
    anse
    -0.30
    iou
    -0.28
    ulum
    -0.27
    berra
    -0.26
    iant
    -0.26
    ialis
    -0.25
     Toll
    -0.25
    mate
    -0.25
    hel
    -0.25
    ÑĤан
    -0.25
    POSITIVE LOGITS
    .Comp
    0.27
    å´ĩ
    0.25
    licer
    0.24
    bands
    0.24
    Powered
    0.24
    (rgb
    0.24
    working
    0.24
    ogan
    0.24
    af
    0.23
    èĬ±çº¹
    0.23
    Activations Density 0.089%

    No Known Activations