© 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. 22-TRANSCODER-HP
    7. 87944
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ABA
    -0.27
    zug
    -0.26
    赢家
    -0.25
     favor
    -0.25
     Sergei
    -0.25
    ØŃت
    -0.25
     realization
    -0.24
    責
    -0.24
    aba
    -0.23
    venience
    -0.23
    POSITIVE LOGITS
    Unnamed
    0.27
     alleged
    0.25
    FromArray
    0.25
    iefs
    0.24
    OOK
    0.24
    _pad
    0.23
     Ive
    0.23
     Everybody
    0.23
    åIJ¯
    0.22
    éĵŃ
    0.22
    Activations Density 0.004%

    No Known Activations