© 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. 96342
    Prev
    Next
    INDEX
    Explanations

    differences

    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
    æĹ¢
    -0.27
    fully
    -0.25
    å±ı
    -0.25
    ivité
    -0.24
    bit
    -0.24
    æĥ³è±¡åĬĽ
    -0.23
    åħ¥åľº
    -0.23
    road
    -0.23
    oping
    -0.23
    Kelly
    -0.23
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.39
     incompatible
    0.39
     different
    0.39
     important
    0.34
    ä¸įä¸Ģæł·çļĦ
    0.34
     homophobic
    0.34
    different
    0.33
     linked
    0.33
     relevant
    0.31
     distinct
    0.31
    Activations Density 0.108%

    No Known Activations