© 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. 54300
    Prev
    Next
    INDEX
    Explanations

    Coagulation/pharmaceuticals

    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
    å±Ģåī¯å±Ģéķ¿
    -0.27
     promot
    -0.26
    endregion
    -0.26
    Ñıд
    -0.26
    -loop
    -0.26
    opolitan
    -0.26
    bos
    -0.25
    loop
    -0.24
    alone
    -0.24
    ãģ«ä¹Ĺ
    -0.24
    POSITIVE LOGITS
    .cg
    0.29
    mentation
    0.27
    meric
    0.27
    ANGED
    0.26
    éĽĨä¸Ń
    0.26
    对å¤ĸ
    0.26
    aternion
    0.25
    UIApplication
    0.25
    好
    0.25
    chen
    0.25
    Activations Density 0.009%

    No Known Activations