© 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. 63854
    Prev
    Next
    INDEX
    Explanations

    comparisons, analogies

    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
    论
    -0.28
    æĢİä¹Īæł·
    -0.26
    ä¸į足以
    -0.26
     intermitt
    -0.25
    åħ³æĢĢ
    -0.25
    munition
    -0.25
    auce
    -0.24
    ZA
    -0.24
    LERÄ°
    -0.24
    mia
    -0.24
    POSITIVE LOGITS
     Ðĺменно
    0.33
    æĶ¹æŃ£
    0.29
    oble
    0.27
    antar
    0.26
    æĶ¹ä¸º
    0.26
    asper
    0.26
    änd
    0.26
    èĥĮ
    0.25
    ä¸ĢåĪ»
    0.25
     именно
    0.24
    Activations Density 4.406%

    No Known Activations