© 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. 43171
    Prev
    Next
    INDEX
    Explanations

    chemical elements

    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
     potassium
    -0.41
     copper
    -0.41
     zinc
    -0.41
     magnesium
    -0.40
     chromium
    -0.40
     selenium
    -0.40
     titanium
    -0.40
     SIL
    -0.39
     silver
    -0.37
     chrome
    -0.37
    POSITIVE LOGITS
    Fe
    0.54
     Fe
    0.51
     Ba
    0.48
    Ba
    0.45
    Ni
    0.43
    Na
    0.41
    Si
    0.41
     Si
    0.40
     Ca
    0.39
     Ce
    0.39
    Activations Density 0.016%

    No Known Activations