© 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. 40928
    Prev
    Next
    INDEX
    Explanations

    Electrical properties and physics

    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
    odem
    -0.32
    angelo
    -0.27
    ODE
    -0.27
    åīij
    -0.25
    cestor
    -0.24
    æµıè§ĪåĻ¨
    -0.24
     beaten
    -0.24
    озд
    -0.24
    lasses
    -0.24
    spacer
    -0.23
    POSITIVE LOGITS
    Say
    0.31
     Say
    0.29
     charge
    0.29
    ãĤ¸ãĥ§ãĥ³
    0.29
    го
    0.27
    mal
    0.26
    oling
    0.26
    imal
    0.25
     direct
    0.25
    intr
    0.25
    Activations Density 0.006%

    No Known Activations