© 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. 30-TRANSCODER-HP
    7. 95747
    Prev
    Next
    INDEX
    Explanations

    line / lines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    werk
    -0.27
    bill
    -0.27
    lage
    -0.25
    ropy
    -0.24
    ãĥĪãĥ«
    -0.23
    è¿Ľå±ķ
    -0.23
    WARE
    -0.23
    SWG
    -0.22
    çŃĴ
    -0.22
    ilty
    -0.22
    POSITIVE LOGITS
     line
    1.88
     lines
    1.76
     Line
    1.64
     Lines
    1.54
    Line
    1.51
    line
    1.48
    _line
    1.43
    -line
    1.43
    Lines
    1.39
    lines
    1.38
    Activations Density 1.858%

    No Known Activations