© 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. 88559
    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
    åıijçĶŁçļĦ
    -0.27
     McMahon
    -0.26
    æ±ł
    -0.26
    åį«çĶŁåģ¥åº·
    -0.26
    .svg
    -0.25
    abilities
    -0.25
    纶
    -0.25
    çģ
    -0.24
     l
    -0.24
    grad
    -0.23
    POSITIVE LOGITS
    thane
    0.27
    念
    0.26
    rame
    0.26
    å®īå®ļ
    0.25
    ány
    0.25
    èĢĮä¸įæĺ¯
    0.25
    æłĹ
    0.25
    éĥ½è§īå¾Ĺ
    0.24
    ült
    0.24
    æĿĵ
    0.24
    Activations Density 2.675%

    No Known Activations

    This feature has no known activations.