© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 130570
    Prev
    Next
    INDEX
    Explanations

    End of phrase/clause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ops
    -0.28
    è¿Ļæł·çļĦ
    -0.28
     '!
    -0.27
    ä»Ļ
    -0.27
    ë§Īëĭ¤
    -0.26
    _operations
    -0.26
    åį°è®°
    -0.26
     operators
    -0.25
    ||
    -0.25
    lox
    -0.25
    POSITIVE LOGITS
    anything
    0.28
    FromClass
    0.28
    å¼Ľ
    0.27
    Earn
    0.25
    çģĮæºī
    0.25
    inherits
    0.24
     frem
    0.24
    æĮĤåı·
    0.24
    xdb
    0.24
    .RUN
    0.24
    Activations Density 75.987%

    No Known Activations