© 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. 35-TRANSCODER-HP
    7. 39758
    Prev
    Next
    INDEX
    Explanations

    housing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     support
    -0.30
     Support
    -0.28
     limit
    -0.28
     guide
    -0.26
     help
    -0.26
     Äijá»ĩ
    -0.26
     cover
    -0.26
     Screens
    -0.26
     shortcuts
    -0.26
     supports
    -0.25
    POSITIVE LOGITS
     housing
    0.88
    housing
    0.81
     Housing
    0.77
    ä½ıæĪ¿
    0.70
     hous
    0.64
     housed
    0.64
    Hosting
    0.63
    Host
    0.62
    host
    0.61
    -host
    0.61
    Activations Density 24.547%

    No Known Activations