© 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. 6758
    Prev
    Next
    INDEX
    Explanations

    code

    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
    éĴĪ对æĢ§
    -0.30
    pora
    -0.28
    åı¦ä¸ĢåįĬ
    -0.27
    minating
    -0.27
     catchy
    -0.26
    dee
    -0.25
    -cn
    -0.24
    ething
    -0.24
    leave
    -0.24
    å¤Ħå¤Ħ
    -0.24
    POSITIVE LOGITS
     upwards
    0.28
    çŃIJ
    0.27
    æģ¯
    0.27
    ç«
    0.26
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.25
    æijĩ
    0.25
    å¾Ģä¸Ĭ
    0.24
     upward
    0.24
    _plain
    0.24
    æī£
    0.24
    Activations Density 0.015%

    No Known Activations