© 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. 54160
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ro
    -0.30
     Mart
    -0.29
    Mart
    -0.28
    upt
    -0.28
    ä¼ĺåħĪ
    -0.26
    asing
    -0.26
    setUp
    -0.26
    ases
    -0.26
    pt
    -0.25
    Portal
    -0.25
    POSITIVE LOGITS
     thr
    0.32
    thr
    0.28
    thers
    0.26
    .googlecode
    0.26
    flo
    0.26
    parsers
    0.25
     IDM
    0.24
    far
    0.24
     ther
    0.23
    æĥĭ
    0.23
    Activations Density 0.077%

    No Known Activations