© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22159
    Prev
    Next
    INDEX
    Explanations

    n

    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
    Negative Logits
     offsetof
    -0.29
    çļĦåį°è±¡
    -0.28
    åľºä¸Ĭ
    -0.27
    è´²
    -0.27
    å¾Ĺèµ·
    -0.26
    主ä½ĵ
    -0.25
     police
    -0.25
    -stage
    -0.24
    ków
    -0.24
    å°ģ
    -0.24
    POSITIVE LOGITS
    çĭIJ
    0.30
    apon
    0.28
    éĿ´
    0.27
    RowIndex
    0.26
    OOT
    0.26
    _CSR
    0.26
    обÑĢаз
    0.26
    ousse
    0.25
    ul
    0.25
     OEM
    0.25
    Activations Density 0.002%

    No Known Activations