© 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. 18-TRANSCODER-HP
    7. 89628
    Prev
    Next
    INDEX
    Explanations

    Code or language fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ«å¤§
    -0.32
    istique
    -0.27
    ä¸ĥ大
    -0.27
    çīĽ
    -0.26
     underestimate
    -0.26
    ticks
    -0.25
    è¿ĺèĥ½
    -0.24
    åĨ²åĬ¨
    -0.24
    åıĪè¦ģ
    -0.24
    &w
    -0.23
    POSITIVE LOGITS
     —↵↵
    0.32
    –↵↵
    0.27
    —↵↵
    0.25
    åįĴ
    0.25
     condemnation
    0.25
    IRT
    0.24
    iot
    0.24
     adel
    0.24
     pros
    0.23
    หย
    0.23
    Activations Density 5.366%

    No Known Activations