© 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. 7446
    Prev
    Next
    INDEX
    Explanations

    phase

    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
    åįĹå±±
    -0.29
     por
    -0.28
    orm
    -0.27
     Por
    -0.26
     above
    -0.25
    _tcb
    -0.24
    above
    -0.24
    æ´ŀ
    -0.24
     foregoing
    -0.23
    sgi
    -0.23
    POSITIVE LOGITS
    apest
    0.25
    zure
    0.25
    .rdf
    0.24
     Others
    0.24
    Ñħо
    0.23
    entifier
    0.23
    éĥ¨éĥ¨éķ¿
    0.23
    ãĤ»ãĥ³ãĤ¿ãĥ¼
    0.23
    ãĥĶãĥ³
    0.23
     McL
    0.23
    Activations Density 0.055%

    No Known Activations