© 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. 4-TRANSCODER-HP
    7. 115
    Prev
    Next
    INDEX
    Explanations

    England locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çķĽ
    -0.30
    Been
    -0.28
    ниÑİ
    -0.26
    ñas
    -0.26
     Shr
    -0.25
    adian
    -0.25
    IMATE
    -0.25
     Onion
    -0.24
    anean
    -0.24
    è°Ĭ
    -0.24
    POSITIVE LOGITS
    顶
    0.25
    yl
    0.25
     touchdown
    0.25
    ç«
    0.24
     equivalents
    0.24
    äºĭå®ŀ
    0.23
    ä»Ģä¹Īæĺ¯
    0.23
    ä»Ģä¹Ī
    0.23
    RG
    0.23
     GPLv
    0.23
    Activations Density 0.015%

    No Known Activations