© 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. 96144
    Prev
    Next
    INDEX
    Explanations

    technical documents/names

    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
    breaking
    -0.32
    break
    -0.30
     balance
    -0.30
     balancing
    -0.30
    Break
    -0.30
     break
    -0.29
     Break
    -0.28
    調
    -0.28
    è°ĥ
    -0.28
     tune
    -0.27
    POSITIVE LOGITS
     SelectList
    0.28
     forks
    0.27
    isis
    0.26
    åıī
    0.25
    秩
    0.25
    æ´Ĺ澡
    0.25
    è½®
    0.24
    .Embed
    0.24
    unes
    0.24
    é¢Ħè§ģ
    0.24
    Activations Density 0.959%

    No Known Activations