© 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. 53437
    Prev
    Next
    INDEX
    Explanations

    "Royal" organizations

    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
    ãĤ¹ãĥļ
    -0.31
    etas
    -0.29
    ety
    -0.28
    uits
    -0.26
    hy
    -0.26
     Sp
    -0.26
     Stay
    -0.26
    ü
    -0.26
    guns
    -0.25
     seals
    -0.25
    POSITIVE LOGITS
     ********************************************************
    0.29
    ableObject
    0.28
    erable
    0.25
    prite
    0.25
    Internet
    0.24
    acad
    0.24
    /fonts
    0.24
    оде
    0.24
    èµ·ä¼ı
    0.24
    æĶ¶è´Ń
    0.23
    Activations Density 0.003%

    No Known Activations