© 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. 229
    Prev
    Next
    INDEX
    Explanations

    lo

    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
    warts
    -0.29
    rote
    -0.29
    (console
    -0.27
    é«ĺåİŁ
    -0.25
    å½Ģ
    -0.25
    ears
    -0.24
    tele
    -0.24
    éĹ¨æ§Ľ
    -0.24
    audi
    -0.24
     FOUR
    -0.24
    POSITIVE LOGITS
     arbit
    0.29
    å±Ģéķ¿
    0.26
     siz
    0.26
     resizable
    0.26
     Leader
    0.25
    Maker
    0.25
    主å¸Ń
    0.25
     bod
    0.24
     ruler
    0.24
     rng
    0.24
    Activations Density 0.005%

    No Known Activations