© 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. 96681
    Prev
    Next
    INDEX
    Explanations

    storytelling and writing

    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
    hape
    -0.25
    rema
    -0.25
     invalidated
    -0.25
    æī¹è¯Ħ
    -0.25
     pemb
    -0.24
    å°ıé¾Ļ
    -0.24
    èĥĸ
    -0.24
    æĸ¥
    -0.24
    arding
    -0.23
     razor
    -0.23
    POSITIVE LOGITS
     conventions
    0.37
     convention
    0.31
    ä¼ł
    0.28
    (logging
    0.28
     practices
    0.27
     cú
    0.27
    çıŃ
    0.26
    è¡¥åĬ©
    0.26
    extended
    0.25
    Extended
    0.25
    Activations Density 0.908%

    No Known Activations