© 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. 98
    Prev
    Next
    INDEX
    Explanations

    available

    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
    enor
    -0.30
    åĪ·æĸ°
    -0.28
    çĹķ
    -0.25
    ç«ł
    -0.25
     capacity
    -0.25
    åĤ¬
    -0.24
    -Ray
    -0.24
    çĻ¾å¹´
    -0.24
     capacities
    -0.24
     anonymously
    -0.24
    POSITIVE LOGITS
    æĶ¾è¿ĩ
    0.31
    eti
    0.29
    ele
    0.25
     tinder
    0.24
    ä½ľä¸ºä¸Ģç§į
    0.24
    ãĤīãģĦ
    0.23
    åĬłåĪĨ
    0.23
     tat
    0.23
    aviest
    0.23
    åĽ½æľīèµĦ产
    0.23
    Activations Density 0.063%

    No Known Activations