© 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. 22-TRANSCODER-HP
    7. 87644
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为æѤ
    -0.28
    _raise
    -0.25
    (Be
    -0.24
     wasted
    -0.24
    å°ı康社ä¼ļ
    -0.24
     najle
    -0.24
    anke
    -0.23
    Äħd
    -0.23
    åıĺå½¢
    -0.23
    -single
    -0.23
    POSITIVE LOGITS
    yen
    0.30
    _regular
    0.26
    _variables
    0.25
    strand
    0.23
     VARIABLES
    0.23
    ERING
    0.23
    _IR
    0.23
    å¿ĥæĦ¿
    0.23
    iri
    0.23
    $view
    0.23
    Activations Density 0.016%

    No Known Activations