© 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. 192
    Prev
    Next
    INDEX
    Explanations

    Florence and Wallace

    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
    ician
    -0.29
    prite
    -0.27
    dera
    -0.26
    dition
    -0.26
    igure
    -0.26
    blick
    -0.26
    edin
    -0.25
    izione
    -0.25
    ritz
    -0.24
    eed
    -0.24
    POSITIVE LOGITS
    /wiki
    0.29
     accommodations
    0.27
    Ñģлав
    0.26
    KS
    0.26
    IMER
    0.25
    otr
    0.24
     louis
    0.23
     crosses
    0.23
    VertexBuffer
    0.23
     Glo
    0.23
    Activations Density 0.014%

    No Known Activations