© 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. 7417
    Prev
    Next
    INDEX
    Explanations

    assembly

    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
    éĻĦåĬłåĢ¼
    -0.27
    (Bit
    -0.25
    plat
    -0.24
    æĹĥ
    -0.24
     RaycastHit
    -0.23
    icot
    -0.23
     gente
    -0.22
    ä½ķ度
    -0.22
    æĭĽåķĨå¼ķ
    -0.22
     Though
    -0.22
    POSITIVE LOGITS
    elor
    0.25
    ment
    0.25
    tures
    0.24
    Arm
    0.24
     sẵn
    0.24
    gan
    0.23
    AndGet
    0.23
    hire
    0.23
    al
    0.23
     arm
    0.23
    Activations Density 2.622%

    No Known Activations