© 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. 130252
    Prev
    Next
    INDEX
    Explanations

    Code and word fragments

    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
     Bubble
    -0.29
    anie
    -0.26
     bubble
    -0.26
     advent
    -0.26
     bounding
    -0.25
    æ©ĺ
    -0.24
    _emit
    -0.24
    .–
    -0.24
    ket
    -0.24
     observation
    -0.24
    POSITIVE LOGITS
    mdir
    0.28
     stirring
    0.27
    æĪij家
    0.27
    ä¸ĭæĸ¹
    0.26
     BELOW
    0.25
    rozen
    0.25
    åĩ¡
    0.24
    ÑĪиб
    0.23
    çŃ
    0.23
    utches
    0.23
    Activations Density 0.075%

    No Known Activations