© 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. 130157
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    foreground
    -0.31
    comings
    -0.29
    Fant
    -0.27
    -middle
    -0.26
    交
    -0.25
     foreground
    -0.25
    forest
    -0.25
    quete
    -0.24
     novelty
    -0.24
    ologies
    -0.24
    POSITIVE LOGITS
    éĺ¶
    0.25
    åĢºåĪ¸
    0.24
    à¹Ģม
    0.23
    æ¯ĶåĪ©
    0.23
     rally
    0.23
    éĽ¢ãĤĮ
    0.23
     financing
    0.23
     leans
    0.23
     egret
    0.22
    urring
    0.22
    Activations Density 8.058%

    No Known Activations