© 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. 129346
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    ãĢĮ
    -0.28
     improbable
    -0.26
     marginal
    -0.26
    Among
    -0.25
     Utility
    -0.25
    æķ´çIJĨ
    -0.25
     reported
    -0.24
    åĸĥ
    -0.24
    èİ·å¾ĹæĦŁ
    -0.24
     utility
    -0.24
    POSITIVE LOGITS
     morals
    0.30
    KI
    0.29
    erra
    0.28
    ebin
    0.27
    QRST
    0.27
    诫
    0.27
    richt
    0.26
    çİ°å¦Ĥä»Ĭ
    0.25
    ä¸Ĭåİ»
    0.25
    amat
    0.25
    Activations Density 0.008%

    No Known Activations