© 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. 23225
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    _ed
    -0.29
    á»ĵng
    -0.28
    ibr
    -0.25
    åIJĮä¸Ģ个
    -0.24
    Enum
    -0.24
    ero
    -0.24
    eds
    -0.24
     frat
    -0.24
    æį¨
    -0.23
    ije
    -0.23
    POSITIVE LOGITS
    ugin
    0.32
    å²IJ
    0.32
    æĪijçĪ±ä½ł
    0.27
    çłĶ究
    0.27
    omid
    0.27
    ghi
    0.26
     nghiên
    0.26
    ushman
    0.25
     RAW
    0.25
    ï¼ļ<
    0.25
    Activations Density 0.000%

    No Known Activations