© 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. 35-TRANSCODER-HP
    7. 40751
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    大家ä¸Ģèµ·
    -0.27
    è¿Ļæł·æīįèĥ½
    -0.25
     Reply
    -0.25
    åĨįåĬłä¸Ĭ
    -0.25
     repayment
    -0.24
    çĦ¶åIJİåĨį
    -0.24
    dress
    -0.23
    èĥĮçĿĢ
    -0.23
    éĤ£æ®µ
    -0.23
    -thirds
    -0.23
    POSITIVE LOGITS
    inge
    0.28
    isodes
    0.26
    SplitOptions
    0.26
    Leaks
    0.25
    ikan
    0.24
    .LA
    0.24
    vel
    0.24
    ooks
    0.24
    arring
    0.24
    into
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.