© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9629
    Prev
    Next
    INDEX
    Explanations

    Questions or self-reflection

    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
    Negative Logits
    n
    -0.27
    æ°ijæĹı
    -0.27
    å®īå±ħ
    -0.26
    culus
    -0.25
    paces
    -0.25
    acom
    -0.25
    mium
    -0.25
    umen
    -0.24
     Commonwealth
    -0.23
    ä¸ŃåѦ
    -0.23
    POSITIVE LOGITS
    -src
    0.29
    phem
    0.27
    ä½Ĩåį´
    0.26
    åį´è¢«
    0.26
    åį´æ²¡æľī
    0.25
     każde
    0.24
     tomb
    0.24
     execution
    0.23
     alph
    0.23
     yet
    0.23
    Activations Density 0.005%

    No Known Activations