© 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. 7496
    Prev
    Next
    INDEX
    Explanations

    computers/servers

    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
    æī£
    -0.29
     Cres
    -0.28
    æĮĩåIJij
    -0.28
     sø
    -0.25
    [sub
    -0.25
    empre
    -0.24
    .$.
    -0.24
    ESP
    -0.24
    äºī缸
    -0.24
    .cz
    -0.24
    POSITIVE LOGITS
    æĪij们å¿ħé¡»
    0.27
    çĶ¨æīĭ
    0.25
    ieving
    0.25
     whom
    0.25
    _MATRIX
    0.24
     affairs
    0.23
    ujemy
    0.23
    åı¯è¡Į
    0.23
     waive
    0.23
    ç¨İ
    0.23
    Activations Density 0.793%

    No Known Activations