© 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. 31-TRANSCODER-HP
    7. 19111
    Prev
    Next
    INDEX
    Explanations

    street address

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     total
    -0.47
    total
    -0.45
    æĢ»
    -0.44
     Total
    -0.39
    Total
    -0.38
    .total
    -0.36
    	total
    -0.35
     TOTAL
    -0.34
    _total
    -0.33
    TOTAL
    -0.33
    POSITIVE LOGITS
     Drive
    0.35
     House
    0.34
     Court
    0.34
     Street
    0.34
     house
    0.32
    Court
    0.32
    -road
    0.31
     Road
    0.31
     Crescent
    0.31
     street
    0.30
    Activations Density 51.510%

    No Known Activations