© 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. 345
    Prev
    Next
    INDEX
    Explanations

    SAP

    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
    hex
    -0.26
    æij¸ç´¢
    -0.25
    çļĦä½ľåĵģ
    -0.25
    abad
    -0.24
    åºŁ
    -0.23
    arged
    -0.23
    Hex
    -0.23
    ops
    -0.23
    _hex
    -0.23
     Algeria
    -0.23
    POSITIVE LOGITS
    å¢ŀ
    0.28
    ughs
    0.27
    åİļ
    0.27
    对æłĩ
    0.26
     Bid
    0.26
     bah
    0.25
    è¾Ī
    0.25
    atha
    0.24
    din
    0.24
    ãĢĤ</
    0.24
    Activations Density 0.005%

    No Known Activations