© 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. 88842
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ACH
    -0.28
     bil
    -0.25
    åįļ
    -0.25
    åĪ«
    -0.25
    ach
    -0.24
    åĨħ容ç®Ģä»ĭ
    -0.24
    _FMT
    -0.24
     digital
    -0.23
    夫人
    -0.23
    è®°
    -0.23
    POSITIVE LOGITS
    èĥ½åĬĽ
    0.27
     Compet
    0.26
    æĺ¯ä¸Ģ件
    0.26
    åĥŃ
    0.26
    éĢĤå½ĵçļĦ
    0.26
    åIJł
    0.25
     Provid
    0.25
    Compet
    0.25
    åĩºèī²çļĦ
    0.25
    tdown
    0.24
    Activations Density 1.286%

    No Known Activations

    This feature has no known activations.