© 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. 19-TRANSCODER-HP
    7. 8381
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perms
    -0.28
    æŃĩ
    -0.26
    abb
    -0.25
    çĦ¶
    -0.25
    åħĢ
    -0.24
    mdb
    -0.24
    aphrag
    -0.24
     petty
    -0.23
    ¡°
    -0.23
    ynchronously
    -0.23
    POSITIVE LOGITS
    EMON
    0.27
    ypy
    0.26
     KP
    0.24
    лин
    0.24
    ktor
    0.24
    彩
    0.24
    [string
    0.24
    ä¹Łä¸įçŁ¥éģĵ
    0.24
    ove
    0.24
    ève
    0.24
    Activations Density 0.098%

    No Known Activations