© 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. 9-TRANSCODER-HP
    7. 29179
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åŃ
    -0.28
    çŃ®
    -0.28
    ä¸įæŃ»
    -0.27
     segue
    -0.26
    (anchor
    -0.25
    ä¸įåģļ
    -0.25
    éĶļ
    -0.25
    æīĢ以æĪij
    -0.24
     Rh
    -0.24
    coil
    -0.24
    POSITIVE LOGITS
     kijken
    0.28
     clashed
    0.26
    amenti
    0.25
    abad
    0.25
    ä¸İåħ¶ä»ĸ
    0.25
    emet
    0.25
    åŁİ
    0.24
     hott
    0.24
     Flynn
    0.24
    onna
    0.24
    Activations Density 12.850%

    No Known Activations