© 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. 112277
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     Office
    -0.26
     softened
    -0.25
    antine
    -0.25
    ä¸Ģ次次
    -0.25
     office
    -0.25
     pieces
    -0.25
    iah
    -0.24
    ä»ĭ
    -0.24
    office
    -0.23
    ä¸įå°ijäºİ
    -0.23
    POSITIVE LOGITS
    åı¦ä¸Ģ个
    0.35
    åı¦å¤ĸä¸Ģ个
    0.33
    another
    0.33
     another
    0.32
    åı¦ä¸Ģ
    0.31
    Another
    0.31
    çĦ¶åIJİåĨį
    0.31
    again
    0.31
    ATER
    0.29
    åıĪ
    0.28
    Activations Density 0.005%

    No Known Activations