© 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. 25125
    Prev
    Next
    INDEX
    Explanations

    common English words

    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
    gon
    -0.28
    gold
    -0.25
    çİ°å®ŀçĶŁæ´»
    -0.25
     rang
    -0.24
    æijĩ头
    -0.23
    æĿª
    -0.23
    åīįä¸ĸ
    -0.23
    cop
    -0.23
     allies
    -0.23
     nau
    -0.23
    POSITIVE LOGITS
    omed
    0.27
     getNode
    0.25
    dna
    0.25
    æݧèĤ¡éĽĨåĽ¢
    0.25
    åĭĥåĭĥ
    0.24
    isman
    0.24
    æĸ«
    0.24
    ofs
    0.24
    egt
    0.24
    åķŁ
    0.24
    Activations Density 0.003%

    No Known Activations