© 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. 63242
    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
    å¸IJ篷
    -0.27
    namese
    -0.27
    оÑĩно
    -0.26
    trash
    -0.25
     van
    -0.25
    ouncil
    -0.25
    maker
    -0.24
    isher
    -0.23
    ovo
    -0.23
    毫æĹł
    -0.23
    POSITIVE LOGITS
    GMEM
    0.28
    æľŁ
    0.27
    åı³è¾¹
    0.26
    èºIJ
    0.26
     pitches
    0.25
    ĥĿ
    0.25
    ipple
    0.25
    Ñĩки
    0.25
    :param
    0.25
     dipping
    0.24
    Activations Density 2.052%

    No Known Activations

    This feature has no known activations.