© 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. 33-TRANSCODER-HP
    7. 53467
    Prev
    Next
    INDEX
    Explanations

    Programming code and files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ps
    -0.26
    æľīéĴ±
    -0.25
     fl
    -0.25
     note
    -0.25
    æ±ī
    -0.25
    جب
    -0.25
    åįķ车
    -0.24
     Reward
    -0.24
    la
    -0.24
    åIJ¬è¯Ŀ
    -0.24
    POSITIVE LOGITS
    æĢĽ
    0.27
    -th
    0.27
    edes
    0.26
     üzerinden
    0.26
    ismic
    0.25
    ä½ľèĢħæīĢæľī
    0.25
    ufact
    0.24
    furt
    0.24
    иж
    0.24
    ä¸ĭ
    0.23
    Activations Density 0.006%

    No Known Activations