© 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. 32-TRANSCODER-HP
    7. 44222
    Prev
    Next
    INDEX
    Explanations

    contains "with"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     med
    -0.31
     bằng
    -0.28
     using
    -0.28
     through
    -0.27
    using
    -0.26
    _using
    -0.26
    ba
    -0.26
     Through
    -0.26
    èĢĮ对äºİ
    -0.25
    å®Įå¤ĩ
    -0.25
    POSITIVE LOGITS
     ith
    0.36
    —with
    0.35
    With
    0.35
    WITH
    0.35
    ITH
    0.35
    -with
    0.35
     withObject
    0.34
    _WITH
    0.34
     With
    0.34
     with
    0.34
    Activations Density 0.028%

    No Known Activations