© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    -ologist

    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
    çļĦåѦçĶŁ
    -0.29
    çŁ¿æ³īæ°´
    -0.27
    orage
    -0.25
    APS
    -0.25
    upe
    -0.25
    upro
    -0.25
    Unt
    -0.24
    uffled
    -0.24
     gig
    -0.24
    gable
    -0.23
    POSITIVE LOGITS
    cplusplus
    0.27
     Nursery
    0.26
    çŃĨ
    0.25
    ôm
    0.24
    çį
    0.24
    é²İ
    0.24
    å³Ĵ
    0.24
    颢
    0.23
     interactions
    0.23
    ÑģÑĤÑĮ
    0.23
    Activations Density 0.017%

    No Known Activations