© 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. 132
    Prev
    Next
    INDEX
    Explanations

    ic

    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
    åĸĤ
    -0.27
    æijĩ
    -0.25
    æľªæĪIJ
    -0.25
     cosmos
    -0.25
     crafts
    -0.24
    haps
    -0.24
     lest
    -0.24
    ç½ijç»ľä¼łæĴŃ
    -0.24
     coax
    -0.24
     Singles
    -0.24
    POSITIVE LOGITS
    满
    0.29
    滿
    0.28
    æ£ł
    0.28
    tdown
    0.25
     Michel
    0.25
    pez
    0.24
    pest
    0.24
    æį·
    0.24
    rador
    0.24
    -relative
    0.24
    Activations Density 1.552%

    No Known Activations