© 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. 130036
    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
    ä¸īæľŁ
    -0.29
    oscopic
    -0.26
    ä¸Ģå°ģ
    -0.26
     tù
    -0.25
    éĢļè¡Įè¯ģ
    -0.25
    æıĸ
    -0.24
    两边
    -0.24
    urnished
    -0.23
    åŀĵ
    -0.23
     endings
    -0.23
    POSITIVE LOGITS
    isl
    0.27
    otto
    0.25
    isle
    0.25
     jet
    0.25
    èĥĸ
    0.24
    _jet
    0.24
    exterity
    0.24
    thin
    0.24
    åĭĩæ°Ķ
    0.24
    稷
    0.24
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.