© 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. 33-TRANSCODER-HP
    7. 54755
    Prev
    Next
    INDEX
    Explanations

    messy code and names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĿĹ
    -0.29
    âm
    -0.28
     met
    -0.26
    VERS
    -0.25
    alchemy
    -0.25
     kup
    -0.25
    medical
    -0.25
    __/
    -0.25
    TEGR
    -0.24
    меÑĤ
    -0.24
    POSITIVE LOGITS
    bach
    0.30
    车
    0.27
    ICC
    0.27
    baugh
    0.26
    æºĨ
    0.26
    ebin
    0.25
     lash
    0.25
    horn
    0.25
    igor
    0.25
    eo
    0.25
    Activations Density 0.008%

    No Known Activations