© 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. 202
    Prev
    Next
    INDEX
    Explanations

    looking

    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
    QUAL
    -0.26
    /workspace
    -0.25
    DAC
    -0.25
    好åIJĹ
    -0.25
    æīģ
    -0.25
     signings
    -0.24
    æŁ°
    -0.24
    _amp
    -0.24
    Qualifier
    -0.23
    Oak
    -0.23
    POSITIVE LOGITS
    ness
    0.35
    ularity
    0.30
     German
    0.30
    eing
    0.29
    iness
    0.28
    宪æ³ķ
    0.28
    äºĨä¸Ģ个
    0.28
    rong
    0.28
    æİ©
    0.28
    German
    0.27
    Activations Density 0.143%

    No Known Activations