© 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. 8670
    Prev
    Next
    INDEX
    Explanations

    exist

    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
    æīĺ
    -0.25
     khảo
    -0.24
    sters
    -0.24
    erin
    -0.23
    Assistant
    -0.23
    ä¼ļ
    -0.23
    çīĪ
    -0.22
    olin
    -0.22
    ëį°
    -0.22
     photos
    -0.22
    POSITIVE LOGITS
    bine
    0.26
    istic
    0.26
    侥幸
    0.25
    ÑĥÑī
    0.25
     blat
    0.24
    ENTA
    0.24
    <![
    0.23
    [".
    0.23
    arda
    0.23
    :';↵
    0.23
    Activations Density 0.669%

    No Known Activations