© 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. 9265
    Prev
    Next
    INDEX
    Explanations

    mode

    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
    ãĤĤãģ®
    -0.26
     Instructions
    -0.23
     Eff
    -0.23
    ARED
    -0.22
    testdata
    -0.22
    å°±è·Ł
    -0.22
    _TRAN
    -0.22
    sis
    -0.21
    丰åİļ
    -0.21
    reetings
    -0.21
    POSITIVE LOGITS
    ities
    0.29
    alty
    0.25
     geral
    0.25
    ä¸įä¿¡
    0.24
    èħĬ
    0.23
    alogy
    0.23
    èĩ£
    0.23
     scho
    0.23
    ways
    0.23
    led
    0.22
    Activations Density 2.235%

    No Known Activations