© 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. 23-TRANSCODER-HP
    7. 24042
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sc
    -0.30
    etal
    -0.29
    è¾¾åĪ°
    -0.29
    cape
    -0.28
    解åĨ³
    -0.27
    请
    -0.27
     cape
    -0.27
    贯穿
    -0.26
     scape
    -0.26
    fo
    -0.26
    POSITIVE LOGITS
    åĹij
    0.26
    orrh
    0.26
     TIMES
    0.25
    REL
    0.25
    pbs
    0.25
    ä¸Ģç¬Ķ
    0.25
    年人
    0.24
    TRAIN
    0.24
    VRT
    0.24
     åķ
    0.24
    Activations Density 0.024%

    No Known Activations

    This feature has no known activations.