© 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. 95881
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĴ¸
    -0.29
     Morse
    -0.28
    urma
    -0.27
     Magnum
    -0.27
    odable
    -0.26
    çĸı
    -0.26
     -:
    -0.26
     Goldberg
    -0.26
     salts
    -0.26
    åįģä¸ĥæĿ¡
    -0.25
    POSITIVE LOGITS
    ä¸Ģå®ļ
    0.36
    ogenesis
    0.27
    åĢij
    0.27
     certain
    0.26
    iframe
    0.26
    OOT
    0.26
     Certain
    0.26
    ience
    0.25
    į°
    0.25
    éĢĶå¾Ħ
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.