© 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. 63774
    Prev
    Next
    INDEX
    Explanations

    Excerpts

    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
     &)
    -0.29
    æĺĻ
    -0.28
    овÑĭм
    -0.26
    æīĢè¬Ĥ
    -0.25
    æѤæĻĤ
    -0.25
    -)
    -0.24
    иÑĤелÑĮно
    -0.24
    :")
    -0.24
    .*)
    -0.23
     $↵
    -0.23
    POSITIVE LOGITS
     happiest
    0.29
     longest
    0.28
     Downs
    0.26
    aton
    0.26
    æµ·å¤ĸ
    0.26
    .forRoot
    0.25
     topped
    0.24
    æ¸ħéĨĴ
    0.24
    æľĢéķ¿
    0.24
     Sanity
    0.24
    Activations Density 1.452%

    No Known Activations