© 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. 64029
    Prev
    Next
    INDEX
    Explanations

    one

    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
    æ¶ī
    -0.33
    à°³
    -0.26
    æīĵæŃ»
    -0.26
    çĨµ
    -0.26
     det
    -0.26
    è¡®
    -0.25
     seg
    -0.24
     entropy
    -0.24
    #ab
    -0.24
    æķ´
    -0.24
    POSITIVE LOGITS
    endum
    0.25
     Hait
    0.24
    ĵåIJį
    0.23
    -ion
    0.23
    conomic
    0.23
    cour
    0.23
     Babylon
    0.23
     Savannah
    0.23
    è¿Ļ个游æĪı
    0.23
    è¿Ļ个人
    0.22
    Activations Density 12.185%

    No Known Activations