© 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. 24-TRANSCODER-HP
    7. 149130
    Prev
    Next
    INDEX
    Explanations

    artistic creations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Fres
    -0.28
    SES
    -0.27
    etration
    -0.26
    agues
    -0.25
    éĽĨè£ħ
    -0.25
    å°¼æĸ¯
    -0.25
     brightest
    -0.25
    æĦıè§ģ
    -0.25
    ¢åįķ
    -0.24
    积åĪĨ
    -0.24
    POSITIVE LOGITS
    ä¾Ľ
    0.27
    ä¾Ľç»Ļ
    0.27
    å¥Ĺ
    0.26
     store
    0.25
    ucher
    0.25
    _pins
    0.24
    BeforeEach
    0.24
    clock
    0.24
    achts
    0.24
     Rays
    0.24
    Activations Density 0.915%

    No Known Activations