© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6502
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    ucha
    -0.28
    culo
    -0.27
    osaur
    -0.27
    ificant
    -0.26
     trick
    -0.25
    èĻ½
    -0.24
     SEQ
    -0.24
     reversing
    -0.24
     sequ
    -0.23
     shield
    -0.23
    POSITIVE LOGITS
     anywhere
    0.27
     Everywhere
    0.26
    -root
    0.24
    èķ
    0.24
    die
    0.24
    æĬĢå¸Ī
    0.24
    ç²¾èĭ±
    0.24
     wherever
    0.24
    igon
    0.24
    åħ¨çIJĥ
    0.24
    Activations Density 0.788%

    No Known Activations