© 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. 141978
    Prev
    Next
    INDEX
    Explanations

    psychological

    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
    inth
    -0.27
     [{'
    -0.25
     amnesty
    -0.24
    éķµ
    -0.24
     Fans
    -0.24
    prises
    -0.23
     apl
    -0.23
    IAL
    -0.23
     Reign
    -0.23
     Manor
    -0.23
    POSITIVE LOGITS
    uran
    0.29
    åĮº
    0.28
    rstrip
    0.27
    å¹´ä¹ĭä¹ħ
    0.26
    æŀģ
    0.25
    ÑĩиÑĤÑĭва
    0.25
    BOSE
    0.25
    带头
    0.24
    ura
    0.24
    imoto
    0.24
    Activations Density 10.288%

    No Known Activations