© 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. 5077
    Prev
    Next
    INDEX
    Explanations

    pregnancy

    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
    monic
    -0.29
    èį¸
    -0.28
    arov
    -0.26
    çī©ä¸ļ管çIJĨ
    -0.26
    该
    -0.24
     courier
    -0.24
    SizePolicy
    -0.24
    滹
    -0.23
    bers
    -0.23
     companion
    -0.23
    POSITIVE LOGITS
     Css
    0.26
     pregn
    0.26
     Trans
    0.25
    ISTR
    0.24
     Recommend
    0.24
    åīĬå¼±
    0.24
    assic
    0.24
     bosses
    0.23
    prepared
    0.23
    INESS
    0.23
    Activations Density 0.265%

    No Known Activations