© 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. 20-TRANSCODER-HP
    7. 107627
    Prev
    Next
    INDEX
    Explanations

    Code and conversation mixed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TZ
    -0.29
    éĻ¤æѤ
    -0.25
    çĥ§
    -0.25
    burger
    -0.24
     tone
    -0.24
    æĻ¨
    -0.24
    äºīåıĸ
    -0.24
    cus
    -0.23
    人æµģ
    -0.23
    éĢļå¾Ģ
    -0.23
    POSITIVE LOGITS
     exhib
    0.27
    esda
    0.25
    fcn
    0.25
     ($)
    0.25
     notices
    0.24
    -cur
    0.24
    iman
    0.24
    BeginInit
    0.24
     unavoidable
    0.24
     responseBody
    0.24
    Activations Density 19.338%

    No Known Activations