© 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. 41443
    Prev
    Next
    INDEX
    Explanations

    Federal

    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
    ersed
    -0.30
    士
    -0.29
    dt
    -0.29
    è´¨
    -0.27
    atri
    -0.26
    AQ
    -0.26
    .getElementsBy
    -0.25
    star
    -0.25
    è´¬
    -0.24
    AES
    -0.24
    POSITIVE LOGITS
     Federal
    0.46
    èģĶéĤ¦
    0.45
     Robert
    0.44
    Federal
    0.43
     federal
    0.41
    Robert
    0.40
     feder
    0.33
     ÑĦедеÑĢ
    0.30
     Rodrigo
    0.29
    Fed
    0.28
    Activations Density 0.010%

    No Known Activations