© 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. 130470
    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
    ptr
    -0.30
    ORLD
    -0.27
     stems
    -0.27
     undert
    -0.27
    dep
    -0.26
    ifiable
    -0.25
     Lind
    -0.25
    çļĦæĺ¯
    -0.25
    åĨįæĿ¥
    -0.24
    ressed
    -0.24
    POSITIVE LOGITS
     Clarkson
    0.28
    imson
    0.27
    ",__
    0.26
    å§IJ妹
    0.25
    移åĪ°
    0.25
    æ´ģåĩĢ
    0.24
    éŨè¯Ĭ
    0.24
    æīĢéľĢè¦ģçļĦ
    0.24
    åįķä¸Ģ
    0.24
    íĺ¼
    0.23
    Activations Density 1.489%

    No Known Activations

    This feature has no known activations.