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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 303
    Prev
    Next
    INDEX
    Explanations

    Twitter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neh
    -0.28
    åĬłçĽŁ
    -0.25
     vej
    -0.25
    âİŀ
    -0.25
    Straight
    -0.24
     INLINE
    -0.24
    stud
    -0.24
    overlap
    -0.24
     muj
    -0.23
    dealloc
    -0.23
    POSITIVE LOGITS
     litter
    0.25
     compound
    0.25
     My
    0.25
    duct
    0.24
     like
    0.24
    ä¸Ģèµ·
    0.24
    .
    0.24
     custody
    0.24
    _INDEX
    0.24
     Mesh
    0.23
    Activations Density 0.038%

    No Known Activations