© 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. 129429
    Prev
    Next
    INDEX
    Explanations

    code snippets/documentation

    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
    客æĪ·æıIJä¾Ľ
    -0.31
    inton
    -0.26
    ercul
    -0.25
    atype
    -0.25
    ROY
    -0.25
    gram
    -0.24
    天çĦ¶
    -0.24
    ä¾ij
    -0.24
    bands
    -0.24
    ripe
    -0.23
    POSITIVE LOGITS
    ä¼Ĺ
    0.25
    缸æ¯Ķ
    0.25
    âĿ
    0.25
    çĽ¾
    0.24
    otted
    0.24
     sys
    0.24
    éĹ´éļĶ
    0.24
    å°ijäºĨ
    0.24
    HLT
    0.23
     interval
    0.23
    Activations Density 1.436%

    No Known Activations