© 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. 7143
    Prev
    Next
    INDEX
    Explanations

    medicine and biology

    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
     велик
    -0.28
    .wr
    -0.27
    夷
    -0.26
     mark
    -0.26
    游
    -0.25
    éľĩ
    -0.25
    rowned
    -0.25
    (write
    -0.24
    å°ļ
    -0.24
    Coll
    -0.24
    POSITIVE LOGITS
    ancing
    0.28
    aring
    0.28
    akra
    0.27
     antid
    0.26
    eft
    0.25
    abinet
    0.24
    iset
    0.24
    conc
    0.24
     doses
    0.24
     pea
    0.24
    Activations Density 0.026%

    No Known Activations