© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42997
    Prev
    Next
    INDEX
    Explanations

    decisions and actions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Abyss
    -0.25
     Nimbus
    -0.25
    ellan
    -0.24
    оÑı
    -0.24
    第ä¸Ģ书记
    -0.23
    åĺĺ
    -0.23
     disemb
    -0.23
     oma
    -0.23
     ByteString
    -0.23
    anean
    -0.23
    POSITIVE LOGITS
     material
    0.32
     Material
    0.32
     captured
    0.28
     strike
    0.28
    owler
    0.27
    ões
    0.27
    needed
    0.26
     strikes
    0.26
     mirror
    0.26
     carried
    0.26
    Activations Density 0.003%

    No Known Activations