© 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. 42286
    Prev
    Next
    INDEX
    Explanations

    Heart and coronary procedures

    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
     heart
    -1.55
     hearts
    -1.39
    å¿ĥ
    -1.38
    heart
    -1.36
     Heart
    -1.32
    Heart
    -1.26
    -heart
    -1.24
    çļĦå¿ĥ
    -1.21
     Hearts
    -1.05
    å¿ĥèĦı
    -1.02
    POSITIVE LOGITS
    .setOutput
    0.24
    cid
    0.24
    ibal
    0.23
    Coding
    0.23
    isons
    0.23
    ffb
    0.23
    _ABI
    0.23
    ccd
    0.23
    isors
    0.23
    (inv
    0.22
    Activations Density 0.055%

    No Known Activations