© 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. 88258
    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
    éī´åĪ«
    -0.29
    lek
    -0.27
    /colors
    -0.27
    otten
    -0.27
    çļĦ积æŀģæĢ§
    -0.26
    çļĦæĥħ绪
    -0.25
    åĪ«
    -0.25
    _colors
    -0.24
    èī²æ³½
    -0.24
    æ´²
    -0.24
    POSITIVE LOGITS
     releg
    0.26
     Laud
    0.26
    ceu
    0.25
    uzzer
    0.24
    .hw
    0.23
    ecure
    0.23
     assum
    0.23
    Chef
    0.23
    -maker
    0.23
    erializer
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.