© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 141899
    Prev
    Next
    INDEX
    Explanations

    Titles of works

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bur
    -0.28
    æ´½
    -0.28
     standing
    -0.27
     talk
    -0.27
     altern
    -0.27
    æµĥ
    -0.25
     None
    -0.25
     tri
    -0.25
    fer
    -0.24
     comb
    -0.24
    POSITIVE LOGITS
     aup
    0.27
    åı¦ä¸Ģä½į
    0.27
    IOS
    0.26
    IFI
    0.25
    HP
    0.25
    æĪĸå°Ĩ
    0.25
    phia
    0.25
     dó
    0.25
    lox
    0.24
    龸çİĭ
    0.24
    Activations Density 25.779%

    No Known Activations