© 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. 96590
    Prev
    Next
    INDEX
    Explanations

    camera/technology specifications

    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
    burgh
    -0.31
    bery
    -0.29
    ç²ĺ
    -0.27
    伯
    -0.27
    æĶĺ
    -0.26
    夹
    -0.26
    æ¿Ģèµ·
    -0.25
    ienne
    -0.25
    imb
    -0.25
    ipt
    -0.25
    POSITIVE LOGITS
    SETS
    0.27
    å®ŀä½ĵ
    0.25
    depart
    0.25
    åĩ½
    0.25
    äch
    0.24
     outbound
    0.24
     Pac
    0.23
    çļĦæĸ¹åIJij
    0.23
     depart
    0.23
     Narc
    0.23
    Activations Density 0.884%

    No Known Activations