© 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. 20-TRANSCODER-HP
    7. 129936
    Prev
    Next
    INDEX
    Explanations

    Writing about people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ourselves
    -0.40
    æĪij们çļĦ
    -0.36
     myself
    -0.35
    æĪijèĩªå·±
    -0.34
    ä½ĨæĪij们
    -0.33
    æĪijçļĦ
    -0.32
    æĪij们éĥ½
    -0.30
     our
    -0.29
    ç»Ļä½łä»¬
    -0.29
    ours
    -0.29
    POSITIVE LOGITS
     themselves
    0.29
    è¶Ĭ好
    0.26
    GenericType
    0.25
    缩水
    0.25
    窥
    0.25
    @admin
    0.25
    plit
    0.25
    åĴĮä»ĸçļĦ
    0.23
    odor
    0.23
     narrower
    0.23
    Activations Density 51.041%

    No Known Activations