© 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. 27-TRANSCODER-HP
    7. 57488
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİīäºĨ
    -0.27
    ↵                    ↵
    -0.27
    åģ¥åħ¨
    -0.26
    uche
    -0.26
    uforia
    -0.25
    rowned
    -0.25
    аÑĤÑĥÑĢ
    -0.24
    æİī
    -0.24
     chic
    -0.23
    Wilson
    -0.23
    POSITIVE LOGITS
     коÑĢпÑĥÑģ
    0.27
     Sociology
    0.27
    åħĶ
    0.24
    主åħ¬
    0.24
    æŃ£æĺ¯åĽłä¸º
    0.24
    åŃĹæ¯į
    0.24
    Resistance
    0.24
    襦
    0.24
     Flux
    0.23
    è®®ä¼ļ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.