© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7165
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    aman
    -0.26
    使ä¹ĭ
    -0.25
    $__
    -0.25
    çĻ½é©¬
    -0.25
    istar
    -0.24
    å®ĥ们
    -0.24
    TN
    -0.24
    çĶ¦
    -0.23
    è§ģæķĪ
    -0.23
     volunt
    -0.23
    POSITIVE LOGITS
    shaw
    0.27
    nowledge
    0.26
    ---↵↵
    0.25
    æijĨ
    0.25
    hole
    0.25
    åĨ·æ¼ł
    0.25
    duct
    0.24
    Explanation
    0.24
     bunker
    0.23
    oting
    0.23
    Activations Density 0.006%

    No Known Activations