© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 7663
    Prev
    Next
    INDEX
    Explanations

    warranty

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
     work
    -0.28
    个交æĺĵ
    -0.26
    缮æłĩä»»åĬ¡
    -0.26
     occupations
    -0.26
     aside
    -0.25
    -span
    -0.25
     Work
    -0.24
    çĭ¸
    -0.24
     union
    -0.24
     begr
    -0.24
    POSITIVE LOGITS
    æı´
    0.27
    èĥĮä¸Ĭ
    0.25
     displacement
    0.24
    nga
    0.24
    åı¤ä»Ĭ
    0.23
    FD
    0.23
    åĥıæĺ¯
    0.23
    esium
    0.23
    Ether
    0.23
    å®ŀçĶ¨æĢ§
    0.23
    Activations Density 0.127%

    No Known Activations