© 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. 9-TRANSCODER-HP
    7. 30079
    Prev
    Next
    INDEX
    Explanations

    Foreign languages/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rott
    -0.27
    ãĥ¼ãĥł
    -0.26
    larından
    -0.25
     dint
    -0.25
    åľ¨è¿Ļç§į
    -0.24
    æĹłåĬ©
    -0.24
    è¿ĻæŶåĢĻ
    -0.24
     BBB
    -0.24
    odu
    -0.24
    ,tr
    -0.24
    POSITIVE LOGITS
     Flask
    0.29
    .DialogResult
    0.27
     uomo
    0.26
    peg
    0.26
    Die
    0.25
    ereo
    0.25
     Die
    0.25
     life
    0.24
     anchors
    0.24
     homme
    0.23
    Activations Density 1.121%

    No Known Activations