© 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. 281
    Prev
    Next
    INDEX
    Explanations

    movable/removable

    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
    >{!!
    -0.29
    cı
    -0.27
    \Base
    -0.27
    xcc
    -0.26
    å°ijåIJĥ
    -0.25
    Ñģи
    -0.24
    æµģåĬ¨æĢ§
    -0.24
    (Environment
    -0.24
    秩
    -0.23
    slick
    -0.23
    POSITIVE LOGITS
    eks
    0.27
    ãģĵãģ¨
    0.27
    unik
    0.26
    unch
    0.26
    unds
    0.25
    çĻ«çĹ«çĹħ
    0.25
    ä¸Ģ件äºĭ
    0.25
    kind
    0.25
    ESS
    0.25
    space
    0.24
    Activations Density 0.162%

    No Known Activations