© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 95767
    Prev
    Next
    INDEX
    Explanations

    bro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organ
    -0.29
    rait
    -0.28
    æĭĮ
    -0.27
    ught
    -0.25
    uvre
    -0.25
    kehr
    -0.24
    è§ĨåIJ¬
    -0.24
    work
    -0.24
    rice
    -0.24
    ilde
    -0.24
    POSITIVE LOGITS
    æī¶
    0.25
    æľĢå°ij
    0.25
    èĩ´
    0.25
    sit
    0.25
    åĪĨåŃIJ
    0.24
     molecular
    0.24
     Molecular
    0.24
     Trophy
    0.24
     provoke
    0.24
    客æĪ·æıIJä¾Ľ
    0.24
    Activations Density 0.001%

    No Known Activations