© 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. 12-TRANSCODER-HP
    7. 23322
    Prev
    Next
    INDEX
    Explanations

    Garbled/Nonsense data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ次æĢ§
    -0.28
     læ
    -0.28
    åIJįçīĩ
    -0.26
    Ùħات
    -0.25
    acles
    -0.24
    icks
    -0.24
    ä¸Ńå±±
    -0.24
    oust
    -0.24
    feit
    -0.24
     XM
    -0.23
    POSITIVE LOGITS
    ĥģ
    0.26
    пÑĥÑģ
    0.25
     sorte
    0.25
    滢
    0.24
    sched
    0.24
    彪
    0.23
    ãĦ§
    0.23
    iffe
    0.23
    bir
    0.23
     Gos
    0.23
    Activations Density 0.000%

    No Known Activations