© 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. 129562
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    polate
    -0.27
    trash
    -0.26
    Thought
    -0.26
     Doctrine
    -0.26
    Trash
    -0.26
    交éĢļ大åѦ
    -0.25
    uality
    -0.25
    å¿ĥä¸ŃçļĦ
    -0.24
    peria
    -0.24
    Tho
    -0.24
    POSITIVE LOGITS
    æľīåIJį
    0.27
    _VC
    0.26
    olic
    0.26
     Turning
    0.25
     discipl
    0.25
    ç¾İ容
    0.25
     discipline
    0.24
    åľ£åľ°
    0.24
     món
    0.24
     sunt
    0.24
    Activations Density 1.281%

    No Known Activations

    This feature has no known activations.