© 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. 108195
    Prev
    Next
    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    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
    çļĦåİŁåĽł
    -0.63
    主è¦ģåİŁåĽł
    -0.60
    åİŁåĽł
    -0.56
    éĩįè¦ģåİŁåĽł
    -0.54
     reasons
    -0.54
    æĺ¯åĽłä¸º
    -0.52
     reason
    -0.51
    çļĦç¼ĺ
    -0.49
    reason
    -0.48
    ç¼ĺ
    -0.48
    POSITIVE LOGITS
    åıį
    0.28
    oksen
    0.27
     Affero
    0.27
    æ£ĺ
    0.27
    discard
    0.24
    hev
    0.24
    ç¹ģ
    0.24
    dot
    0.24
    /firebase
    0.24
    coc
    0.24
    Activations Density 23.253%

    No Known Activations