© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6515
    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
    NotEmpty
    -0.27
    ccione
    -0.26
    gency
    -0.25
    éħįæľī
    -0.25
    erals
    -0.25
    utt
    -0.24
    .toJSONString
    -0.24
    çļĦæĥħæĦŁ
    -0.24
    -strokes
    -0.24
    客æĪ·éľĢæ±Ĥ
    -0.24
    POSITIVE LOGITS
    å¤įä¹ł
    0.26
    åıijæī¬
    0.26
    rew
    0.25
    æĸ¹
    0.25
    çľ¼åħī
    0.24
    æĢĿç´¢
    0.24
     once
    0.24
    amm
    0.23
    æ°ijæĶ¿
    0.23
     review
    0.23
    Activations Density 0.042%

    No Known Activations

    This feature has no known activations.