© 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. 20-TRANSCODER-HP
    7. 141702
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opi
    -0.32
    lero
    -0.28
    é¹ĥ
    -0.26
    ãģľ
    -0.25
    OMATIC
    -0.25
    ilion
    -0.25
    Ñīи
    -0.25
     diálogo
    -0.25
     Fro
    -0.25
    еÑģÑĮ
    -0.24
    POSITIVE LOGITS
    ä¸į失
    0.26
     Banks
    0.26
    -UA
    0.25
    æ¸ħåĩī
    0.25
    ipline
    0.25
     ?><?
    0.24
    gua
    0.24
    éŃĶ鬼
    0.24
    ergy
    0.24
    paren
    0.24
    Activations Density 4.636%

    No Known Activations

    This feature has no known activations.