© 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. 88148
    Prev
    Next
    INDEX
    Explanations

    metadata

    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
    NodeType
    -0.26
    ich
    -0.25
    cake
    -0.25
     amplified
    -0.24
    node
    -0.24
    Cro
    -0.23
    amp
    -0.23
    _amp
    -0.23
    che
    -0.23
    bidden
    -0.23
    POSITIVE LOGITS
    uze
    0.27
    å¨ĺå¨ĺ
    0.26
     stripping
    0.25
    审è§Ĩ
    0.25
    вл
    0.24
    iniz
    0.23
    ÑģпоÑĢ
    0.23
    ä¼łè¾¾
    0.23
    VISION
    0.23
    å°ģéĶģ
    0.23
    Activations Density 0.353%

    No Known Activations