© 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. 25-TRANSCODER-HP
    7. 109194
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folk
    -0.29
    'Ãł
    -0.27
    çļĦ好å¤Ħ
    -0.27
    inded
    -0.25
     creature
    -0.25
    roy
    -0.24
    éĿ´
    -0.24
    ä¾Ŀèµĸ
    -0.24
     Tribune
    -0.23
    TEE
    -0.23
    POSITIVE LOGITS
    éĩį大
    0.29
    upply
    0.27
     Sad
    0.26
    plementation
    0.25
    ramid
    0.25
     Supply
    0.25
    lake
    0.25
    ngen
    0.25
     pys
    0.24
    Supply
    0.24
    Activations Density 0.133%

    No Known Activations

    This feature has no known activations.