© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7505
    Prev
    Next
    INDEX
    Explanations

    period

    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
    alles
    -0.27
     ass
    -0.26
    rapy
    -0.26
     assignable
    -0.26
    è¦ģç´§
    -0.25
    eldon
    -0.25
    æī«çłģ
    -0.25
    gree
    -0.24
    mium
    -0.24
    por
    -0.24
    POSITIVE LOGITS
    æĪ¶
    0.24
     Bas
    0.24
    /release
    0.23
    æĺ¾
    0.23
    Markup
    0.22
    IfExists
    0.22
     NOM
    0.22
    åľ¨åħ¨çIJĥ
    0.21
    åĵ¡
    0.21
    release
    0.21
    Activations Density 2.026%

    No Known Activations