© 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. 54524
    Prev
    Next
    INDEX
    Explanations

    Code/non-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
    Not in Any Lists

    No Comments

    Negative Logits
    dling
    -0.31
    ibbon
    -0.28
    tra
    -0.27
    itta
    -0.27
    tha
    -0.27
     inf
    -0.26
    oller
    -0.26
    .fhir
    -0.26
     Cutting
    -0.25
    Purpose
    -0.25
    POSITIVE LOGITS
    ugin
    0.27
    对她
    0.26
     (!!
    0.25
    对ä»ĸ
    0.24
    人åijĺ
    0.24
    -store
    0.24
     offsetof
    0.24
    éģ½
    0.24
    ä¸įå¾Ĺå·²
    0.24
    iniz
    0.23
    Activations Density 0.010%

    No Known Activations