© 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. 54600
    Prev
    Next
    INDEX
    Explanations

    Code and non-natural language

    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
    isan
    -0.27
    оÑģÑĤоÑı
    -0.26
    åĩŃ
    -0.26
    Toast
    -0.25
    çĿĢæīĭ
    -0.25
    obl
    -0.25
     ans
    -0.25
     perman
    -0.24
    å¾Ħ
    -0.24
    ENSE
    -0.24
    POSITIVE LOGITS
    amide
    0.30
    Sl
    0.27
     Sl
    0.26
    slide
    0.25
    æ¤ħ
    0.25
     slipped
    0.25
    åħħ
    0.24
     NET
    0.24
    hibit
    0.24
     slip
    0.23
    Activations Density 0.003%

    No Known Activations