© 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. 19-TRANSCODER-HP
    7. 7871
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¹Ī
    -0.29
    ILER
    -0.27
    onders
    -0.26
    æľ´ç´ł
    -0.26
    aille
    -0.25
     invite
    -0.25
    æĬķ稿
    -0.25
    æĮij
    -0.25
    agedList
    -0.25
    èŃ
    -0.24
    POSITIVE LOGITS
    å¸Ī
    0.26
    師
    0.25
    éºŁ
    0.25
    ìĿµ
    0.25
     Mega
    0.25
    éĥİ
    0.25
     Tomorrow
    0.24
    åİŁä»¶
    0.24
     Sandwich
    0.24
    (formatter
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.