© 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. 95996
    Prev
    Next
    INDEX
    Explanations

    sentence/sentences

    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
     Line
    -0.40
     line
    -0.38
     Lines
    -0.36
    Line
    -0.36
    _line
    -0.35
    -Line
    -0.34
    .Line
    -0.34
     ligne
    -0.34
    (Line
    -0.33
    LINE
    -0.33
    POSITIVE LOGITS
    æĹłå£°
    0.30
     referring
    0.28
     refer
    0.27
     introdu
    0.26
     structure
    0.26
    Ïį
    0.25
     conserv
    0.24
    Structure
    0.24
     gre
    0.24
     Idea
    0.24
    Activations Density 0.928%

    No Known Activations