© 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. 98118
    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
    å±Ģéĥ¨
    -0.27
    rov
    -0.27
    被åĬ¨
    -0.26
    SEA
    -0.25
    MMM
    -0.25
    orio
    -0.25
    è¿ĻèĪ¬
    -0.25
    ä¸ĸä¸Ĭ
    -0.24
    ey
    -0.24
    ria
    -0.24
    POSITIVE LOGITS
    elson
    0.30
    ÑĤаÑĢ
    0.28
     contrary
    0.27
     Await
    0.25
    pur
    0.25
    -paced
    0.25
     curt
    0.25
     (;;)
    0.24
    _seconds
    0.24
     Meter
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.