© 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. 52592
    Prev
    Next
    INDEX
    Explanations

    Scientific/Technical texts

    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
    æ³±
    -0.30
    ac
    -0.29
    taÅĤ
    -0.28
    itary
    -0.26
    ä¸Ĭä¸ĭ
    -0.26
    opot
    -0.25
    ot
    -0.25
    arine
    -0.25
    RL
    -0.24
    ourt
    -0.24
    POSITIVE LOGITS
    AN
    0.31
    an
    0.31
     prohibit
    0.28
    nor
    0.26
     Ferguson
    0.26
    any
    0.26
    anse
    0.26
    anz
    0.25
    ANE
    0.25
    æĸĹ
    0.25
    Activations Density 0.130%

    No Known Activations