© 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. 107027
    Prev
    Next
    INDEX
    Explanations

    disrupting

    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
     repeatedly
    -0.29
    l
    -0.29
     LPARAM
    -0.28
     perror
    -0.25
    -ts
    -0.25
     lä
    -0.24
    没æľī
    -0.24
    å¨Ī
    -0.24
    åĨį
    -0.24
    ế
    -0.24
    POSITIVE LOGITS
    edList
    0.32
    -ahead
    0.27
    edException
    0.27
    eren
    0.27
    åħĪè¿ĽæĬĢæľ¯
    0.26
     Ruf
    0.25
    åĵģç§į
    0.25
    vale
    0.25
    anus
    0.24
    豪å®ħ
    0.24
    Activations Density 18.029%

    No Known Activations