© 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. 129460
    Prev
    Next
    INDEX
    Explanations

    Locations/Organizations/Events

    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
    鬼
    -0.28
    ações
    -0.24
    xcb
    -0.24
    å«īå¦Ĵ
    -0.23
    linkplain
    -0.23
    ANI
    -0.23
    æŁ´
    -0.23
    头çĸ¼
    -0.23
    é¢Ħæµĭ
    -0.23
    nej
    -0.22
    POSITIVE LOGITS
    ä¸į解
    0.32
    bourne
    0.26
     surre
    0.26
    ople
    0.26
    eenth
    0.26
     balk
    0.26
    pad
    0.25
    çĬĢ
    0.25
    afe
    0.25
     cep
    0.24
    Activations Density 54.433%

    No Known Activations