© 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. 96672
    Prev
    Next
    INDEX
    Explanations

    variety of topics

    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
    Only
    -0.27
     Only
    -0.26
    _ONLY
    -0.26
    端æŃ£
    -0.26
     only
    -0.25
    éļ»
    -0.25
    igmat
    -0.24
    åīį端
    -0.23
    Improved
    -0.23
    дон
    -0.23
    POSITIVE LOGITS
    global
    0.37
     globally
    0.37
     worldwide
    0.36
     global
    0.36
     amount
    0.35
     size
    0.34
    åħ¨çIJĥ
    0.34
    åħ¨å±Ģ
    0.33
    size
    0.32
     combined
    0.30
    Activations Density 0.101%

    No Known Activations