© 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. 6475
    Prev
    Next
    INDEX
    Explanations

    code and transcripts

    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
     Garland
    -0.27
    god
    -0.27
    ndon
    -0.27
    æī«ä¸Ģæī«
    -0.25
    ewe
    -0.25
    精度
    -0.25
    noDB
    -0.24
     resultCode
    -0.24
    æ°ĸ
    -0.24
    rab
    -0.24
    POSITIVE LOGITS
    æ²»
    0.25
    _DOMAIN
    0.25
    _LOGGER
    0.25
    ember
    0.25
    æĢ§
    0.23
    ysis
    0.23
     attracted
    0.23
    BED
    0.23
     Cost
    0.23
    áo
    0.23
    Activations Density 0.008%

    No Known Activations