© 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. 31-TRANSCODER-HP
    7. 19462
    Prev
    Next
    INDEX
    Explanations

    Arthur

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    infra
    -0.30
     infra
    -0.29
     work
    -0.28
    åı¹
    -0.26
    abet
    -0.25
    iona
    -0.25
    æĢĿèĢĥ
    -0.25
    ele
    -0.25
    Inflater
    -0.24
     historical
    -0.24
    POSITIVE LOGITS
     Alive
    0.25
    ism
    0.24
    äºĮåįģåĽĽ
    0.24
     vivo
    0.23
    )||(
    0.23
    åĨĻåĩº
    0.23
     cuff
    0.23
    éĶ²
    0.23
    éĴ³
    0.23
    нибÑĥдÑĮ
    0.23
    Activations Density 0.005%

    No Known Activations