© 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
    2. Qwen3-4B
    3. 22-TRANSCODER-HP
    4. 112384
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    inet
    -0.30
    erez
    -0.28
    ĮĢ
    -0.26
    tiny
    -0.25
     strokeWidth
    -0.25
     espec
    -0.25
    为空
    -0.25
    è½½
    -0.24
    _simps
    -0.24
    缼
    -0.24
    POSITIVE LOGITS
    ummies
    0.28
    abus
    0.27
    .Copy
    0.25
    onium
    0.24
    ulary
    0.24
    icals
    0.24
     Fusion
    0.23
    æ°ijä¼Ĺ
    0.23
    roach
    0.23
    library
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.