© 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. 130076
    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
    æļĿ
    -0.27
     Others
    -0.27
    ÑģÑĤвие
    -0.25
    PIP
    -0.25
    oine
    -0.25
    äººåľ¨
    -0.25
     others
    -0.25
    æĭ¼åij½
    -0.25
    others
    -0.24
    æĹģ
    -0.24
    POSITIVE LOGITS
    æįĤ
    0.29
    flip
    0.29
    opoly
    0.25
    _MSK
    0.25
    çŁ¥è¯ĨçĤ¹
    0.24
     switched
    0.24
    å¼Ī
    0.24
    allowed
    0.24
    åıĤå±ķ
    0.24
    emap
    0.23
    Activations Density 20.859%

    No Known Activations

    This feature has no known activations.