© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8343
    Prev
    Next
    INDEX
    Explanations

    Geographic locations

    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
     diff
    -0.28
     Liber
    -0.28
     hair
    -0.27
    ence
    -0.27
    erland
    -0.26
     proof
    -0.25
    BBC
    -0.25
    èĤ²
    -0.24
     haircut
    -0.24
    ç§ijæĬĢ大åѦ
    -0.24
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.28
    åij¨æľŁ
    0.28
    -members
    0.27
    ritz
    0.27
    -cycle
    0.26
    апÑĢ
    0.25
    ä¸Ģè¾ĪåŃIJ
    0.25
    å®ķ
    0.24
     UNICODE
    0.24
    ائز
    0.23
    Activations Density 0.066%

    No Known Activations