© 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. 7630
    Prev
    Next
    INDEX
    Explanations

    Web pages and articles

    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
    è·Ŀ离
    -0.28
    åłĤ
    -0.28
    charted
    -0.25
    _LVL
    -0.25
    è´¦
    -0.24
     wasn
    -0.24
    ."[
    -0.24
     Turns
    -0.24
    ais
    -0.23
    bus
    -0.23
    POSITIVE LOGITS
     pm
    0.26
    udes
    0.26
     supplement
    0.26
    ilogy
    0.25
     PM
    0.25
    gie
    0.24
    åĪĨæŀIJ
    0.24
    iedad
    0.24
    	pm
    0.24
    pm
    0.24
    Activations Density 0.010%

    No Known Activations