© 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. 33-TRANSCODER-HP
    7. 53186
    Prev
    Next
    INDEX
    Explanations

    Ships and nautical topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     super
    -0.30
    åī¯éĻ¢éķ¿
    -0.29
    æīĩ
    -0.29
    -inv
    -0.27
     rains
    -0.27
    eller
    -0.27
    ä¸Ģåı£
    -0.27
     inv
    -0.26
     globals
    -0.26
    è¶ħ
    -0.26
    POSITIVE LOGITS
    念头
    0.27
     rigs
    0.27
     Rig
    0.26
    rig
    0.26
    ande
    0.25
     rig
    0.25
    è´°
    0.25
    ç»ıæµİ
    0.25
    nie
    0.24
    intr
    0.24
    Activations Density 0.018%

    No Known Activations