© 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. 30-TRANSCODER-HP
    7. 95828
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odied
    -0.26
    hsi
    -0.26
    opol
    -0.25
    çĶ¨é¤IJ
    -0.24
    éĹ»
    -0.24
    hit
    -0.23
    çĵł
    -0.23
    éĩįè¦ģåĽłç´ł
    -0.23
    Worksheet
    -0.23
    æĶ¥
    -0.23
    POSITIVE LOGITS
    strap
    0.28
    离ä¸įå¼Ģ
    0.26
    ewan
    0.25
    bak
    0.25
    åħ¬å¼Ģ
    0.24
    zap
    0.24
    -map
    0.23
     justification
    0.23
    =min
    0.23
    -min
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.