© 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. 129371
    Prev
    Next
    INDEX
    Explanations

    numbers, measurements, and versions

    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
    ovel
    -0.26
    WARD
    -0.25
    ÑĢод
    -0.24
    (Global
    -0.24
    aphrag
    -0.24
    Pipe
    -0.23
    ongsTo
    -0.23
     TODAY
    -0.23
    /Form
    -0.23
    .pad
    -0.23
    POSITIVE LOGITS
    å®Į
    0.27
    å°Ħ
    0.25
    æīĭç»Ń
    0.24
    =?,
    0.24
    è¶Ĭ
    0.24
    é»ĺ
    0.23
    åĪĨåĪ«ä¸º
    0.23
    å°ıäºİ
    0.23
     burn
    0.23
     enumerator
    0.23
    Activations Density 0.041%

    No Known Activations