© 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. 23-TRANSCODER-HP
    7. 23749
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    band
    -0.29
    å¸
    -0.28
    師
    -0.26
    å¸Ī
    -0.25
    mpeg
    -0.25
     bande
    -0.25
    转载请
    -0.25
    NewLabel
    -0.24
    èį£èªī称åı·
    -0.24
    KeyId
    -0.24
    POSITIVE LOGITS
     heads
    0.28
    jas
    0.25
    头
    0.25
    ured
    0.24
    缸åºĶçļĦ
    0.24
    é¦ĸå±Ĭ
    0.24
    è°ĥéħį
    0.23
    æģģ
    0.23
     klar
    0.23
    衬衫
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.