© 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. 89329
    Prev
    Next
    INDEX
    Explanations

    Words ending in "er"

    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
    otor
    -0.26
     lod
    -0.26
     scen
    -0.26
    anie
    -0.26
    osp
    -0.25
    éĺ³åİ¿
    -0.25
    .fig
    -0.24
    orting
    -0.24
    å«ģ
    -0.24
    '](
    -0.24
    POSITIVE LOGITS
    acf
    0.28
    ä»ħ
    0.27
     bulund
    0.27
    鲨
    0.25
    )application
    0.24
    ä»ħä¾Ľ
    0.24
    åħķ
    0.24
     Tek
    0.24
    mour
    0.24
    åħ¼åħ·
    0.23
    Activations Density 5.378%

    No Known Activations