© 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. 19382
    Prev
    Next
    INDEX
    Explanations

    countries and locations

    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
    éŃģ
    -0.28
     Regions
    -0.27
    ivor
    -0.26
    åĮº
    -0.26
     zones
    -0.26
     Zones
    -0.25
    åıĺéĢŁ
    -0.25
    rego
    -0.25
    oming
    -0.24
     regions
    -0.24
    POSITIVE LOGITS
    åĽ½å®¶
    1.34
    åĽ½
    1.21
    åľĭ家
    1.16
     nation
    1.10
     national
    1.07
     country
    1.04
    åĽ½ãģ®
    1.00
     Nation
    0.98
    åľĭ
    0.96
    åĽ½åº¦
    0.96
    Activations Density 9.656%

    No Known Activations