© 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. 242
    Prev
    Next
    INDEX
    Explanations

    ce

    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
    woord
    -0.28
    igkeit
    -0.27
     setInput
    -0.26
    ä¹łè¿ij
    -0.25
     autoComplete
    -0.24
     düzey
    -0.24
    <![
    -0.24
     prox
    -0.24
    å°Ĩè¿ij
    -0.24
     samen
    -0.23
    POSITIVE LOGITS
    çĥŃæĥħ
    0.27
    sg
    0.26
     RM
    0.25
    SE
    0.25
    主è¦ģ
    0.25
    ãģĦãģĭ
    0.24
     Pere
    0.24
    سÙĪر
    0.24
    çĤ¹è¯Ħ
    0.24
     se
    0.24
    Activations Density 0.006%

    No Known Activations