© 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. 374
    Prev
    Next
    INDEX
    Explanations

    nuclear

    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
    ói
    -0.26
    ublic
    -0.26
    ronic
    -0.25
    ê¸Ī
    -0.25
    æłĵ
    -0.24
    OptionPane
    -0.24
    emoth
    -0.24
    uplicate
    -0.24
    ulses
    -0.23
    æĸ°çīĪ
    -0.23
    POSITIVE LOGITS
     compact
    0.26
    çķ¥
    0.25
    orum
    0.25
    è¾±
    0.25
     Against
    0.24
     against
    0.24
     discipline
    0.24
     membership
    0.23
     cos
    0.23
    Against
    0.23
    Activations Density 0.037%

    No Known Activations