© 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. 108085
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     toler
    -0.28
    ä»Ģä¹Īæł·
    -0.27
     catalyst
    -0.26
    .Timeout
    -0.26
    顶å±Ĥ
    -0.25
    }->
    -0.24
    .sul
    -0.24
    alan
    -0.24
    itus
    -0.24
    -sama
    -0.24
    POSITIVE LOGITS
    elist
    0.29
    éĥ½ä¸į
    0.27
    icture
    0.26
     Seiten
    0.25
    istically
    0.25
    0.25
    çľĭåĪ°
    0.25
    åѦçĶŁä»¬
    0.25
     davon
    0.25
     Morrison
    0.24
    Activations Density 1.511%

    No Known Activations