© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 274
    Prev
    Next
    INDEX
    Explanations

    scar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alien
    -0.28
    htm
    -0.27
    è¾į
    -0.27
    gue
    -0.26
    æĪijè¿ĺæĺ¯
    -0.24
    èļ±
    -0.24
    ugen
    -0.24
     artık
    -0.24
    contained
    -0.24
    ié
    -0.24
    POSITIVE LOGITS
    (s
    0.26
    “In
    0.25
    èĪĨ
    0.25
     optimized
    0.24
    ortho
    0.23
    ulates
    0.23
     bas
    0.23
    ç«¿
    0.23
     Visual
    0.22
    leur
    0.22
    Activations Density 0.007%

    No Known Activations