© 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. 141439
    Prev
    Next
    INDEX
    Explanations

    of

    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
     _.
    -0.27
     (_.
    -0.27
    !!.
    -0.26
    infra
    -0.26
     removal
    -0.25
    ency
    -0.25
    æĪª
    -0.25
    以åIJİ
    -0.25
     ones
    -0.25
    ä»ĬåIJİ
    -0.25
    POSITIVE LOGITS
     CONSTANTS
    0.28
    pecting
    0.27
    aldo
    0.27
    поÑĢÑĤ
    0.25
    sez
    0.25
    裾
    0.24
    cem
    0.24
    tridges
    0.24
    unted
    0.24
     Mud
    0.23
    Activations Density 6.649%

    No Known Activations