© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162067
    Prev
    Next
    INDEX
    Explanations

    Irish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ķĮ
    -0.28
    æĢİä¹ĪåĬŀ
    -0.27
    own
    -0.27
     Rajasthan
    -0.27
    æī¿
    -0.26
    DMI
    -0.25
    ä¹Ī
    -0.25
    åĽĽäºĶ
    -0.25
    麼
    -0.24
    ῳ
    -0.24
    POSITIVE LOGITS
     Dublin
    0.35
    .ie
    0.34
     Belfast
    0.31
    çĪ±å°Ķåħ°
    0.28
     Irish
    0.28
    ^K
    0.28
    è´µéĺ³
    0.26
     drama
    0.26
    夯å®ŀ
    0.26
     Ireland
    0.26
    Activations Density 0.081%

    No Known Activations