© 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. 142269
    Prev
    Next
    INDEX
    Explanations

    Fernando

    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
    ÇĶ
    -0.32
    ogen
    -0.26
    ivities
    -0.26
    ysql
    -0.25
    æ°ijçĶŁ
    -0.24
    upon
    -0.24
     Metric
    -0.24
    hood
    -0.24
    vro
    -0.24
    untu
    -0.24
    POSITIVE LOGITS
    è¿·ä¿¡
    0.30
     leider
    0.29
    æºŁ
    0.25
    ç§Ģ
    0.24
    éĶĭ
    0.24
     present
    0.24
    è´»
    0.24
     spir
    0.24
    trad
    0.24
     trespass
    0.24
    Activations Density 10.751%

    No Known Activations