© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    Informal communications/business contexts

    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
    elman
    -0.28
     reloading
    -0.27
     sworn
    -0.27
     yourself
    -0.26
     myself
    -0.26
    亲身
    -0.26
     лиÑĩно
    -0.26
    ÑĢÑĥз
    -0.26
     oneself
    -0.26
    rades
    -0.26
    POSITIVE LOGITS
    讲
    0.33
    å¦ĤæŀľæĪij们
    0.31
    ç»ĻæĪij们
    0.30
    让æĪij们
    0.30
    为æĪij们
    0.29
    unk
    0.28
     Cons
    0.28
    ç½ĺ
    0.27
    pk
    0.27
     cons
    0.26
    Activations Density 0.347%

    No Known Activations