© 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. 30225
    Prev
    Next
    INDEX
    Explanations

    capacity

    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
    è·ŁæĪij
    -0.28
    pret
    -0.26
    IRM
    -0.26
    uple
    -0.26
    vertime
    -0.25
    plete
    -0.25
    ä¸İä¸ŃåĽ½
    -0.25
    è·Łå¥¹
    -0.25
    SENS
    -0.24
    æķĪåĬĽ
    -0.24
    POSITIVE LOGITS
     fix
    0.30
    åĢ¨
    0.24
     ak
    0.24
     upgrade
    0.24
     enc
    0.23
     inn
    0.23
     airs
    0.23
    anske
    0.23
     touchdown
    0.23
     climb
    0.23
    Activations Density 2.227%

    No Known Activations