© 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. 19-TRANSCODER-HP
    7. 6472
    Prev
    Next
    INDEX
    Explanations

    Punctuation and common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľª
    -0.42
    è¿ĺ没æľī
    -0.39
    å°ļæľª
    -0.38
    缺åı£
    -0.36
    è¿ĺ没
    -0.36
     unseen
    -0.36
     chÆ°a
    -0.35
    没è§ģè¿ĩ
    -0.35
    è¿ĺæľª
    -0.35
    æľªæĪIJ
    -0.32
    POSITIVE LOGITS
    å¯ĵ
    0.26
    stä
    0.25
    寤
    0.25
    èµĭ
    0.25
    shaw
    0.25
     shrinking
    0.25
     Richt
    0.25
    pet
    0.25
    å°ıèħ¿
    0.24
    ÑĪиÑĢ
    0.24
    Activations Density 0.242%

    No Known Activations