© 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. 64079
    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
    ç»ĨåĪĨ
    -0.29
     liberty
    -0.27
    ัย
    -0.27
    æīįçŁ¥éģĵ
    -0.25
     Äijảo
    -0.25
    á»Ĵ
    -0.24
    \Lib
    -0.24
     closing
    -0.23
    çĪ±å°Ķ
    -0.23
    åİĭåĪ¶
    -0.23
    POSITIVE LOGITS
     subject
    0.27
    zion
    0.26
     activated
    0.26
    subject
    0.25
    ipop
    0.25
    çĹķ
    0.24
    迹
    0.24
     #+#
    0.24
    å¿Ĺ
    0.24
    REA
    0.23
    Activations Density 6.096%

    No Known Activations

    This feature has no known activations.