© 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. 107801
    Prev
    Next
    INDEX
    Explanations

    time periods/dating

    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
    åĵģçīĮçļĦ
    -0.27
    qh
    -0.25
    åĵģç§į
    -0.24
    regar
    -0.24
    unread
    -0.23
    olin
    -0.23
    lers
    -0.23
    EEE
    -0.23
    çĹĴ
    -0.23
    鸥
    -0.23
    POSITIVE LOGITS
    acerb
    0.28
    æİī
    0.26
    -before
    0.25
    åĢĴ
    0.25
    ativity
    0.25
    è¡°
    0.24
    omb
    0.24
    sense
    0.23
    Before
    0.23
    为ä»Ģä¹Īä¼ļ
    0.23
    Activations Density 4.801%

    No Known Activations