© 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. 89145
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
    <?=
    -0.04
    ',{↵
    -0.04
    warts
    -0.04
     RuntimeObject
    -0.04
    ä¸Ńå°ıåŀĭ
    -0.04
    械
    -0.04
    "><?=
    -0.04
     stems
    -0.03
    äººåľ¨
    -0.03
     synthes
    -0.03
    POSITIVE LOGITS
    abel
    0.04
    relationship
    0.04
    ool
    0.04
     NEC
    0.04
    èį¯
    0.04
    çİ°åĩº
    0.04
    ãģĿ
    0.04
    rea
    0.04
    ãĥĭãĥĥãĤ¯
    0.04
    åįĸåĩº
    0.04
    Activations Density 29.652%

    No Known Activations