© 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. 32-TRANSCODER-HP
    7. 42196
    Prev
    Next
    INDEX
    Explanations

    "too" phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ次
    -0.34
    çĶļèĩ³
    -0.32
    ä¸ĢæŦ
    -0.31
    oque
    -0.28
    æĿ¥èĩª
    -0.28
    Once
    -0.28
    once
    -0.26
    PEC
    -0.25
     once
    -0.25
    éªĨ
    -0.24
    POSITIVE LOGITS
     ever
    0.50
    Ever
    0.38
     EVER
    0.38
    ever
    0.36
     for
    0.36
     given
    0.34
     Ever
    0.34
    -ever
    0.34
     to
    0.34
     most
    0.29
    Activations Density 0.004%

    No Known Activations