© 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. 96095
    Prev
    Next
    INDEX
    Explanations

    mask

    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
     side
    -0.37
     Side
    -0.34
    Side
    -0.33
    ç«ĭ
    -0.33
     put
    -0.32
     pose
    -0.30
     Put
    -0.30
    侧
    -0.30
    side
    -0.29
     puts
    -0.29
    POSITIVE LOGITS
    çĶŁçī©åѦ
    0.29
    å·¥ä½ľçļĦ
    0.29
     replaced
    0.27
    efs
    0.27
    éħĿ
    0.26
     weakest
    0.26
    æĩĤå¾Ĺ
    0.25
     replacement
    0.25
     replacements
    0.25
     baff
    0.25
    Activations Density 0.886%

    No Known Activations