© 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. 5012
    Prev
    Next
    INDEX
    Explanations

    quite

    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
    è¾Ī
    -0.24
    书记
    -0.24
    vector
    -0.23
     Flash
    -0.23
    U
    -0.23
     nächste
    -0.23
    :
    -0.22
     vector
    -0.22
     Ha
    -0.22
    ä¸Ģä½ĵ
    -0.22
    POSITIVE LOGITS
    egie
    0.25
     (>
    0.24
    ogui
    0.24
    witter
    0.23
    ician
    0.23
    omat
    0.23
    ened
    0.22
     albeit
    0.22
    BCM
    0.22
    anst
    0.22
    Activations Density 0.790%

    No Known Activations