© 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. 64002
    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
    æłī
    -0.29
    -hot
    -0.29
     drift
    -0.25
     advising
    -0.25
     wÅĤasne
    -0.24
    обÑĢ
    -0.24
    zell
    -0.24
    管çIJĨä¸Ńå¿ĥ
    -0.23
    åĩºæīĭ
    -0.23
    踵
    -0.23
    POSITIVE LOGITS
     soundtrack
    0.24
    å¼ķ
    0.24
    iphone
    0.24
    åIJ¬å¾Ĺ
    0.24
    Leader
    0.24
     listener
    0.24
    afari
    0.23
    _listener
    0.23
     svensk
    0.23
    åĪĻ
    0.23
    Activations Density 4.583%

    No Known Activations

    This feature has no known activations.