© 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. 63497
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    UBLE
    -0.31
    èµ·æĿ¥
    -0.27
    è¿Ļæīįæĺ¯
    -0.26
     çĽ
    -0.24
    éķ§
    -0.24
    èµ·äºĨ
    -0.24
    ajas
    -0.23
    åħ¼å®¹
    -0.23
    çĤ¹åįĬ
    -0.23
    èµ·æĿ¥äºĨ
    -0.23
    POSITIVE LOGITS
    foundation
    0.27
    berg
    0.26
    __.__
    0.24
    issa
    0.24
    bourg
    0.24
    æľįåĬ¡æľºæŀĦ
    0.24
    ást
    0.24
    omin
    0.24
    pgsql
    0.24
    ninger
    0.24
    Activations Density 0.288%

    No Known Activations