© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    Transcriptions of conversations

    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
     coincidence
    -0.29
     sheer
    -0.27
     plain
    -0.26
    _SEPARATOR
    -0.25
     disgr
    -0.25
     `'
    -0.24
    ewolf
    -0.24
    _PRICE
    -0.24
    dek
    -0.24
    ä¸ĭ次
    -0.24
    POSITIVE LOGITS
    uts
    0.31
     NotImplemented
    0.27
     Clamp
    0.26
    ();}↵
    0.25
    ""↵
    0.24
    社ä¼ļåĮĸ
    0.24
    ãģĵãĤĵãģ«
    0.23
    "}}↵
    0.23
    éĺ²çģ«
    0.23
    uby
    0.23
    Activations Density 0.014%

    No Known Activations