© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 9589
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alleges
    -0.28
    opo
    -0.28
    -ra
    -0.26
     transfer
    -0.25
    RESSION
    -0.25
    æĢ»
    -0.25
    ÏĮ
    -0.25
    -short
    -0.24
    ORM
    -0.24
     might
    -0.24
    POSITIVE LOGITS
     Karn
    0.29
    ibling
    0.26
     Vie
    0.25
    çķħéĶĢ
    0.25
    åħ¶ä¸ŃåĮħæĭ¬
    0.25
    ĸī
    0.24
    peria
    0.24
    otive
    0.24
    符åı·
    0.23
    oogle
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.