© 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. 6770
    Prev
    Next
    INDEX
    Explanations

    Colors

    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
    æĹłéĻIJ
    -0.26
     clic
    -0.26
    drag
    -0.25
    iced
    -0.25
    cover
    -0.24
    æļ´éĽ¨
    -0.24
    éĹŃçݯ
    -0.24
    å¯ĨåĪĩ缸åħ³
    -0.24
    主ä¸ļ
    -0.23
    anes
    -0.23
    POSITIVE LOGITS
     GTA
    0.27
    matchCondition
    0.27
    PullParser
    0.26
    ç«
    0.25
    ($__
    0.24
    ceptor
    0.24
    .qq
    0.24
    erÃŃa
    0.23
    afs
    0.23
    tees
    0.23
    Activations Density 0.799%

    No Known Activations