© 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. 7575
    Prev
    Next
    INDEX
    Explanations

    Stopwords

    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
    ipers
    -0.28
    KeyType
    -0.28
    ieren
    -0.25
    irmed
    -0.25
    ierung
    -0.24
    REM
    -0.24
    é¢ĺ主
    -0.24
    ÑİÑĢ
    -0.24
    artic
    -0.23
     RCS
    -0.23
    POSITIVE LOGITS
    peech
    0.26
    mith
    0.24
    åĪĨå±Ģ
    0.24
    lyn
    0.24
     slit
    0.23
     sl
    0.23
    едÑĮ
    0.23
    åī¯å±Ģéķ¿
    0.22
    稹
    0.22
    inda
    0.22
    Activations Density 0.008%

    No Known Activations