© 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. 6006
    Prev
    Next
    INDEX
    Explanations

    writing/publishing

    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
     syndrome
    -0.27
     pulled
    -0.26
     rude
    -0.26
    zug
    -0.24
    åĢĻéĢī
    -0.24
    åĪĻ
    -0.24
    è¾Ļ
    -0.24
    è¾Ħ
    -0.23
     repertoire
    -0.23
     judge
    -0.23
    POSITIVE LOGITS
    é¢ģ
    0.27
     SEL
    0.25
    ISS
    0.25
    iss
    0.25
     Paleo
    0.25
    licensed
    0.24
    .hom
    0.24
    طاÙĦ
    0.24
    ç®Ń
    0.24
    isher
    0.24
    Activations Density 0.024%

    No Known Activations