© 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. 30-TRANSCODER-HP
    7. 96473
    Prev
    Next
    INDEX
    Explanations

    festivals and holidays

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    observer
    -0.28
    _KIND
    -0.27
    iani
    -0.27
    Observer
    -0.26
    flare
    -0.25
     Observatory
    -0.25
    ites
    -0.25
    (obs
    -0.25
    nees
    -0.25
    件
    -0.24
    POSITIVE LOGITS
    edo
    0.34
    allon
    0.30
    uin
    0.29
    ĤŃ
    0.28
    upy
    0.28
    älle
    0.27
    gne
    0.27
    ulous
    0.27
     day
    0.26
    稳
    0.26
    Activations Density 0.011%

    No Known Activations