© 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. 19-TRANSCODER-HP
    7. 6437
    Prev
    Next
    INDEX
    Explanations

    Movement, direction

    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
    eth
    -0.27
    _eth
    -0.25
     вал
    -0.25
    +N
    -0.25
    ULA
    -0.25
     suppress
    -0.25
    loth
    -0.25
    .Formatter
    -0.25
     italic
    -0.24
    åĬ¨
    -0.24
    POSITIVE LOGITS
    æĸ¹åľĨ
    0.29
    .googleapis
    0.26
    icense
    0.25
    Ñīе
    0.25
    Glass
    0.24
    .SERVER
    0.24
    çİ»çĴĥ
    0.24
    棱
    0.24
    æľīæīĢ
    0.23
    glass
    0.23
    Activations Density 0.058%

    No Known Activations