© 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. 130106
    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
    olated
    -0.25
     âĶľ
    -0.23
    ogan
    -0.23
    .Scope
    -0.23
     Sys
    -0.23
     Nichols
    -0.22
    ï¼ļ↵↵
    -0.22
    -encoded
    -0.22
     retries
    -0.22
     Ammo
    -0.21
    POSITIVE LOGITS
    è¿Ļ段
    0.25
    åijĺ
    0.23
    ercul
    0.22
    -pill
    0.22
     flaming
    0.22
    VML
    0.22
    è¿Ļæī¹
    0.21
    æĬ»
    0.21
    çĥŁ
    0.21
     promot
    0.21
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.