© 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. 6035
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    LI
    -0.28
    prot
    -0.28
    -Level
    -0.25
     注
    -0.24
    _PW
    -0.24
    ga
    -0.24
     eds
    -0.24
    鹤
    -0.24
    yles
    -0.23
     Hampton
    -0.23
    POSITIVE LOGITS
    ->$
    0.32
    /jav
    0.27
    èĻ
    0.27
    $__
    0.26
    sburg
    0.26
    /release
    0.26
    ($__
    0.25
    ively
    0.25
    atively
    0.24
    entimes
    0.24
    Activations Density 0.004%

    No Known Activations