© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161765
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Desktop
    -0.27
    Degrees
    -0.26
    inds
    -0.26
    åĪĨæł¡
    -0.24
    jt
    -0.24
    StdString
    -0.24
    ANI
    -0.24
    eller
    -0.24
     hospitalized
    -0.23
    ç§į
    -0.23
    POSITIVE LOGITS
    第ä¸ĢæĿ¡
    0.26
     Term
    0.26
    ivate
    0.25
    Upgrade
    0.25
    ucer
    0.24
     Lord
    0.24
    rosis
    0.24
    å¦Ĥæľīä¾µæĿĥ
    0.24
     Mej
    0.23
     ↵↵
    0.23
    Activations Density 0.007%

    No Known Activations