© 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. 24035
    Prev
    Next
    INDEX
    Explanations

    creation/establishment (past-tense)

    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
     gran
    -0.27
    ализ
    -0.26
     Clement
    -0.26
    "/
    -0.26
    appropri
    -0.25
    许åı¯
    -0.25
    uming
    -0.25
     materiaÅĤ
    -0.25
    å¹´å¼Ģå§ĭ
    -0.24
    uzzer
    -0.24
    POSITIVE LOGITS
    ives
    0.31
    ä¸įä½ı
    0.28
    èݲ
    0.26
    骧
    0.26
     stagger
    0.25
    IVES
    0.25
    èį·
    0.25
    ILE
    0.25
    comings
    0.25
    anje
    0.24
    Activations Density 0.004%

    No Known Activations