© 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. 91
    Prev
    Next
    INDEX
    Explanations

    ented

    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
    eth
    -0.28
    ɹ
    -0.26
    榨
    -0.25
    species
    -0.23
     Species
    -0.23
    ooter
    -0.23
     "]
    -0.23
     oc
    -0.23
     boost
    -0.23
    æķijæĬ¤
    -0.22
    POSITIVE LOGITS
    æIJŀå¾Ĺ
    0.28
    èįı
    0.28
    -logo
    0.26
     themselves
    0.25
    ÑĢав
    0.25
    imized
    0.24
    åıĤèĢĥèµĦæĸĻ
    0.24
    ابة
    0.24
     covered
    0.23
    .findIndex
    0.23
    Activations Density 0.011%

    No Known Activations