© 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. 7493
    Prev
    Next
    INDEX
    Explanations

    Factual writing

    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
    çĶ³ãģĹ
    -0.27
    killer
    -0.25
    å±Ĭ
    -0.24
    ÑĦа
    -0.24
     мног
    -0.24
     Mercy
    -0.24
    æĥ®
    -0.24
    omic
    -0.24
     Pty
    -0.23
    rick
    -0.23
    POSITIVE LOGITS
    abbit
    0.27
    unnel
    0.26
    åħ¶å®ĥéĹ®é¢ĺ
    0.25
    好äºĭ
    0.25
    é²ľ
    0.25
    åĢŁ
    0.25
    æĪij说
    0.24
    otta
    0.24
     [{
    0.24
    [${
    0.24
    Activations Density 0.032%

    No Known Activations