© 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. 34
    Prev
    Next
    INDEX
    Explanations

    iers

    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
    ез
    -0.30
    oint
    -0.26
    åIJĦ项
    -0.24
    оÑĤ
    -0.24
    çļĦæĸĩç«ł
    -0.24
    ###
    -0.24
     оÑĤноÑĪении
    -0.24
    ayout
    -0.23
     yüz
    -0.23
     polluted
    -0.23
    POSITIVE LOGITS
    bomb
    0.30
    IBC
    0.28
     Manit
    0.28
    SAM
    0.28
    DDL
    0.27
    mlin
    0.26
    ingly
    0.26
    bish
    0.25
    sam
    0.25
    ncoder
    0.25
    Activations Density 0.763%

    No Known Activations