© 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. 63824
    Prev
    Next
    INDEX
    Explanations

    as like

    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
    auc
    -0.26
    å·´æĭī
    -0.26
    .blob
    -0.26
     tended
    -0.25
     Israelis
    -0.25
    /stat
    -0.24
     unde
    -0.24
     conspic
    -0.24
     Lair
    -0.24
     escaped
    -0.23
    POSITIVE LOGITS
    åı«åģļ
    0.34
    åı«
    0.32
    enal
    0.28
    agal
    0.26
    æĪĸå¤ļ
    0.26
     Frozen
    0.25
    çĶļ
    0.25
    人æµģ
    0.24
    getReference
    0.24
    大åħ¨
    0.24
    Activations Density 12.590%

    No Known Activations