© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8202
    Prev
    Next
    INDEX
    Explanations

    Code and Math

    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
    -delay
    -0.28
    éģ
    -0.27
     delays
    -0.27
    延
    -0.27
    -rel
    -0.26
    çİĩè¾¾
    -0.26
    åŀĭä¼ģä¸ļ
    -0.25
    Ñİ
    -0.25
    oor
    -0.24
    _Delay
    -0.24
    POSITIVE LOGITS
    çŀĮ
    0.28
    ern
    0.27
    kommen
    0.26
    ERN
    0.25
     **/↵
    0.25
     Exiting
    0.25
    (Sender
    0.25
     memcmp
    0.25
     stir
    0.24
    total
    0.24
    Activations Density 0.004%

    No Known Activations