© 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. 107456
    Prev
    Next
    INDEX
    Explanations

    Code is working

    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
    _MARKER
    -0.29
    leh
    -0.28
    æĦĢ
    -0.26
    IDGET
    -0.26
    asher
    -0.25
    ık
    -0.25
     mere
    -0.25
    .TestTools
    -0.24
    mitter
    -0.24
    ä¸į符
    -0.24
    POSITIVE LOGITS
     Epid
    0.31
     country
    0.28
    á¸į
    0.28
    _ep
    0.26
    trade
    0.25
     trade
    0.25
    bindings
    0.25
    åĶIJæľĿ
    0.25
    çī¹çĤ¹
    0.24
     ++$
    0.24
    Activations Density 11.705%

    No Known Activations