© 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. 63042
    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
    æ¯ı
    -0.26
    æľºèĥ½
    -0.26
    adal
    -0.25
    æŁ¥èİ·
    -0.25
    åĪĨè¡Į
    -0.25
     libr
    -0.25
    ationToken
    -0.25
    çī¹çĤ¹
    -0.24
    aroo
    -0.24
    åĬ¨æijĩ
    -0.24
    POSITIVE LOGITS
    ume
    0.31
    ppe
    0.31
    uc
    0.30
    umes
    0.27
    sf
    0.26
    ALTH
    0.26
    bn
    0.26
    è¯ģæį®
    0.26
    UC
    0.25
    agher
    0.25
    Activations Density 6.256%

    No Known Activations

    This feature has no known activations.