© 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. 54619
    Prev
    Next
    INDEX
    Explanations

    Various excerpts and sentences

    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
    \\"
    -0.29
    çĪ¬
    -0.28
    \\\
    -0.28
    taken
    -0.27
    \\\\
    -0.27
    \\
    -0.27
    hape
    -0.27
    wear
    -0.27
    tam
    -0.26
    rel
    -0.26
    POSITIVE LOGITS
    éĥ¨éŨ
    0.29
     wollen
    0.28
     scen
    0.27
    ¥
    0.27
    注æĺİåĩºå¤Ħ
    0.26
    该
    0.26
    å·¨
    0.26
    ¦
    0.26
     abdomen
    0.25
     jackpot
    0.25
    Activations Density 0.086%

    No Known Activations