© 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. 64492
    Prev
    Next
    INDEX
    Explanations

    colon punctuation

    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
    éĻħ
    -0.30
     $?
    -0.26
    داء
    -0.25
    zf
    -0.24
    aser
    -0.24
    cas
    -0.23
    èĢĥèĻij
    -0.23
    ä¹¾
    -0.23
    çģĮ
    -0.23
    å¹¹
    -0.23
    POSITIVE LOGITS
    essel
    0.28
    oldown
    0.27
    åıŁ
    0.25
    éĢļçķħ
    0.25
    Demon
    0.24
    annot
    0.24
    çį¨ç«ĭ
    0.24
    ylene
    0.24
    emale
    0.23
    iid
    0.23
    Activations Density 1.922%

    No Known Activations