© 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. 53615
    Prev
    Next
    INDEX
    Explanations

    chemistry terms

    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
    utow
    -0.30
    uten
    -0.30
    uti
    -0.29
     capit
    -0.28
    werk
    -0.28
    è¯Ŀ说
    -0.28
    çĽĹ
    -0.27
    YT
    -0.26
    .staff
    -0.26
     ut
    -0.25
    POSITIVE LOGITS
    zier
    0.28
     chloride
    0.27
     experiments
    0.26
    çĬ¶æĢģä¸ĭ
    0.25
    §
    0.25
    chemes
    0.25
    зов
    0.24
     pot
    0.24
    æ°¯
    0.24
    _CLASSES
    0.24
    Activations Density 0.093%

    No Known Activations