© 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. 108217
    Prev
    Next
    INDEX
    Explanations

    forward slash

    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
    ,cv
    -0.30
     whit
    -0.27
     uk
    -0.26
     cv
    -0.25
    usercontent
    -0.24
    à¸Ńà¸ģ
    -0.24
    inars
    -0.24
    纺
    -0.24
    infos
    -0.24
    çĶŁæ´»åŀĥåľ¾
    -0.24
    POSITIVE LOGITS
    .TryParse
    0.30
    ç°¿
    0.28
     FAR
    0.27
    ä»Ģä¹Īåij¢
    0.26
     {}).
    0.26
    rieb
    0.25
    ä¸įåıĺ
    0.25
    为åħ¶
    0.24
    “↵↵
    0.24
     SAFE
    0.24
    Activations Density 13.048%

    No Known Activations