© 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. 22-TRANSCODER-HP
    7. 129658
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isme
    -0.28
    å¸ĥæĭī
    -0.28
    INCLUDED
    -0.25
    èĽĬ
    -0.25
    ponsored
    -0.24
     emailing
    -0.24
    æ¹ĸåĮº
    -0.24
     immersive
    -0.23
     Ston
    -0.23
    gov
    -0.23
    POSITIVE LOGITS
    åıijçİ°
    0.28
    è¿ħéĢŁ
    0.26
    arent
    0.26
    æĬ¬
    0.25
    段
    0.25
    åĩºåľº
    0.25
     <![
    0.24
    ınt
    0.24
    agos
    0.24
    çĽĺ
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.