© 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. 18-TRANSCODER-HP
    7. 89517
    Prev
    Next
    INDEX
    Explanations

    prototype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pagesize
    -0.25
     ffmpeg
    -0.25
    ãĥĨãĤ£ãĥ³ãĤ°
    -0.25
    åĢ¾æĸľ
    -0.25
     INST
    -0.24
     Riy
    -0.24
    VERT
    -0.24
    osten
    -0.24
    ertools
    -0.24
    .setter
    -0.23
    POSITIVE LOGITS
    åIJ¬åıĸ
    0.27
    åı¬
    0.27
    aled
    0.25
    lesh
    0.24
    ationToken
    0.24
    æī©
    0.24
    oodle
    0.24
     expansions
    0.24
    Absent
    0.24
    ollipop
    0.24
    Activations Density 5.358%

    No Known Activations