© 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. 43509
    Prev
    Next
    INDEX
    Explanations

    code/equations

    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
     seventy
    -0.84
     sixty
    -0.80
     forty
    -0.79
     fifty
    -0.76
     fifteen
    -0.76
     thirty
    -0.76
     seven
    -0.75
     nineteen
    -0.74
     ninety
    -0.73
     thirteen
    -0.73
    POSITIVE LOGITS
    £
    0.25
    .CreateInstance
    0.24
    âĺ°
    0.23
    Äİ
    0.23
    aders
    0.23
    Enumerable
    0.22
    ethylene
    0.22
    >Returns
    0.22
     Stocks
    0.22
    ---</
    0.22
    Activations Density 0.005%

    No Known Activations