© 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. 23108
    Prev
    Next
    INDEX
    Explanations

    metals/alloys

    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
    å¼ıçļĦ
    -0.30
    compression
    -0.27
    atten
    -0.26
    EEK
    -0.26
    quo
    -0.24
    é¢ł
    -0.24
    Compression
    -0.24
    (fh
    -0.23
     compression
    -0.23
    æĽĿåħī
    -0.23
    POSITIVE LOGITS
    rear
    0.26
    raisal
    0.26
    追
    0.24
    ster
    0.24
    éļıæŶéļıåľ°
    0.24
    ↵                ↵
    0.24
    udson
    0.24
    undle
    0.24
    aisy
    0.24
    lide
    0.23
    Activations Density 0.000%

    No Known Activations