© 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. 44134
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ICH
    -0.29
     crud
    -0.26
    ALE
    -0.25
    ãĤ¢ãĥ«
    -0.25
    DAQ
    -0.24
     Rem
    -0.24
    acro
    -0.24
    rem
    -0.24
    REM
    -0.24
    é£ı
    -0.24
    POSITIVE LOGITS
    RIES
    0.27
    imos
    0.25
    baar
    0.25
    åıŃ
    0.25
    agner
    0.25
     merits
    0.25
    ={({
    0.24
     cons
    0.24
    osa
    0.24
     conduc
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.