© 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. 107493
    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
    .AI
    -0.29
    -Russian
    -0.25
    aged
    -0.25
    å£ģåŀĴ
    -0.25
     mocker
    -0.24
    æŁģ
    -0.24
     ÑģкаÑĩ
    -0.24
    URED
    -0.23
    artz
    -0.23
    çĤ¹æ»´
    -0.23
    POSITIVE LOGITS
     blo
    0.25
    æľºä½ĵ
    0.24
     merit
    0.24
    Vote
    0.24
     Models
    0.24
     trapping
    0.24
     Profession
    0.24
    鸽
    0.24
     ruling
    0.24
    PRE
    0.24
    Activations Density 0.648%

    No Known Activations

    This feature has no known activations.