© 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. 63719
    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
    çļĦèĥĮåIJİ
    -0.30
    éĮ
    -0.28
    èĥĮåIJİ
    -0.28
     thuê
    -0.28
    社ä¼ļ稳å®ļ
    -0.27
     prem
    -0.27
     éĶ
    -0.26
     containers
    -0.26
     against
    -0.26
    解åĨ³æĸ¹æ¡Ī
    -0.25
    POSITIVE LOGITS
    ений
    0.31
    éĩįå·¥
    0.28
    akah
    0.27
    æ®ĸ
    0.26
    ÑĥÑĢÑģ
    0.25
    ickers
    0.25
    —they
    0.24
    Cad
    0.24
     Kelley
    0.24
     Bloody
    0.24
    Activations Density 1.170%

    No Known Activations

    This feature has no known activations.