© 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. 53369
    Prev
    Next
    INDEX
    Explanations

    prefixes and constants

    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
    导èĪª
    -0.28
    umas
    -0.26
    locks
    -0.26
    æĪIJ为ä¸ĢåIJį
    -0.25
    imid
    -0.24
    çĪ¶
    -0.24
    æĬĵä½ı
    -0.24
    locked
    -0.24
    (parent
    -0.23
    coc
    -0.23
    POSITIVE LOGITS
     semi
    0.31
     sem
    0.28
    semi
    0.27
    åĤ¬åĮĸåīĤ
    0.27
    sem
    0.26
     un
    0.26
    ti
    0.26
     blade
    0.26
    arte
    0.26
     quasi
    0.25
    Activations Density 0.034%

    No Known Activations