© 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. 111721
    Prev
    Next
    INDEX
    Explanations

    Start of sentences/articles

    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
     mnie
    -0.26
    uguay
    -0.25
    äºĽ
    -0.25
    æĪijçİ°åľ¨
    -0.24
     Legend
    -0.24
    phase
    -0.24
    æĪij们çİ°åľ¨
    -0.24
     unfortunate
    -0.24
    (.)
    -0.24
     phases
    -0.24
    POSITIVE LOGITS
    äºĶ大
    0.29
    ä¸Ĭçľĭ
    0.27
    åĽĽå¤§
    0.27
    åħŃ大
    0.27
    ä¸ī大
    0.26
    .bp
    0.25
    两大
    0.25
    ÑĪиÑĢ
    0.25
    ä¸Ģçľĭ
    0.25
    æİĮæݧ
    0.25
    Activations Density 0.001%

    No Known Activations