© 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. 33-TRANSCODER-HP
    7. 52938
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½ĨæĪij
    -0.26
    说æĪij
    -0.25
     We
    -0.25
     You
    -0.24
    çݰ身
    -0.24
    sonian
    -0.24
     They
    -0.24
    .uni
    -0.24
    PRESENT
    -0.24
    artin
    -0.24
    POSITIVE LOGITS
     nature
    0.30
    wer
    0.27
     Nature
    0.26
     ab
    0.26
    Nature
    0.26
    nature
    0.26
    iad
    0.26
    adan
    0.26
    aba
    0.26
    EMENT
    0.25
    Activations Density 0.024%

    No Known Activations