© 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. 21921
    Prev
    Next
    INDEX
    Explanations

    architecture or code

    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
    å¼ı
    -0.28
    LEX
    -0.26
    activation
    -0.24
    icture
    -0.24
    Buffers
    -0.24
    ipop
    -0.24
    ives
    -0.24
    ergy
    -0.23
    泸
    -0.23
    åIJİèĢħ
    -0.23
    POSITIVE LOGITS
    åħ¬åı¸å°Ĩ
    0.26
    ÑĢедел
    0.26
    .toJSON
    0.26
    rails
    0.25
     divides
    0.25
    igon
    0.25
     disappoint
    0.24
    cms
    0.24
    #=
    0.24
    ç«ĭ
    0.23
    Activations Density 0.001%

    No Known Activations