© 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. 87864
    Prev
    Next
    INDEX
    Explanations

    Oper

    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
     Ever
    -0.28
     Vis
    -0.27
    iversal
    -0.27
    piece
    -0.27
    AtPath
    -0.25
     Associated
    -0.25
     Collections
    -0.24
     threesome
    -0.24
     Result
    -0.24
     Quickly
    -0.24
    POSITIVE LOGITS
    lining
    0.31
     reflecting
    0.25
    å·«
    0.24
    çª
    0.24
    ieres
    0.23
    Ä°Z
    0.23
    Ľ
    0.23
    mine
    0.23
    å¼Ĥåij³
    0.23
    æīĵçĿĢ
    0.23
    Activations Density 0.005%

    No Known Activations