© 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. 6604
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    ä¸ŃåİŁ
    -0.27
    anners
    -0.24
    iteDatabase
    -0.24
    (strcmp
    -0.23
    IFIER
    -0.23
    åĪĹåĩº
    -0.23
    strcmp
    -0.23
    [@
    -0.23
     Fallon
    -0.23
    clin
    -0.23
    POSITIVE LOGITS
    fel
    0.26
     prosec
    0.24
     continual
    0.24
     bail
    0.23
     hybrid
    0.22
    è´°
    0.22
    :disable
    0.22
    è°ĭ
    0.22
    æijĦ
    0.22
    stag
    0.22
    Activations Density 0.049%

    No Known Activations