© 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. 40966
    Prev
    Next
    INDEX
    Explanations

    fixing facts

    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
    xmax
    -0.28
     hbox
    -0.28
    xFD
    -0.27
    ionate
    -0.24
    Appearance
    -0.24
    .hr
    -0.24
    çķħ
    -0.23
    ymax
    -0.23
     rod
    -0.23
    pository
    -0.23
    POSITIVE LOGITS
     fact
    0.40
    fact
    0.33
    _fact
    0.32
     Fact
    0.30
     fixing
    0.30
     missing
    0.30
     Missing
    0.29
    .checked
    0.29
     fixed
    0.29
    åĽºå®ļ
    0.29
    Activations Density 0.001%

    No Known Activations