© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 108496
    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
    åľĥ
    -0.28
    ASF
    -0.28
    æ¹Ħ
    -0.25
    SetValue
    -0.24
    _foot
    -0.24
    åħ¶ä¸Ńæľī
    -0.24
    ên
    -0.23
     паÑĢÑĤ
    -0.23
    uru
    -0.23
    ioneer
    -0.23
    POSITIVE LOGITS
    ateria
    0.32
    tti
    0.26
    zych
    0.24
    ç´§
    0.24
    rais
    0.23
    ython
    0.23
    Statics
    0.23
    Ñģим
    0.23
    iscrimination
    0.23
    beros
    0.23
    Activations Density 39.082%

    No Known Activations

    This feature has no known activations.