© 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. 6272
    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
     others
    -0.29
    彬
    -0.28
    ÑĭÑĪ
    -0.27
     Abyss
    -0.27
    nder
    -0.26
    3
    -0.25
    others
    -0.24
     sqr
    -0.24
    UCH
    -0.24
    .awt
    -0.24
    POSITIVE LOGITS
    antidad
    0.27
    åľ¨ä¹İ
    0.26
    CADE
    0.26
    çļĦ缮åħī
    0.24
    åĿIJèIJ½
    0.24
    anos
    0.24
     Bris
    0.24
    çļĦçĪ¶äº²
    0.24
    äch
    0.23
    Ĭ¶
    0.23
    Activations Density 0.019%

    No Known Activations