© 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. 23-TRANSCODER-HP
    7. 25579
    Prev
    Next
    INDEX
    Explanations

    innovation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĬį
    -0.26
    壳
    -0.25
    KP
    -0.24
    #ac
    -0.23
    viz
    -0.23
    ValuePair
    -0.23
    anking
    -0.23
    éŀĺ
    -0.23
    ]+=
    -0.23
    %S
    -0.23
    POSITIVE LOGITS
     developments
    0.32
     improvements
    0.32
     revolution
    0.29
     advancements
    0.28
     development
    0.27
     integr
    0.27
    åıijå±ķçļĦ
    0.26
     improvement
    0.25
    ç½®
    0.24
     left
    0.24
    Activations Density 0.182%

    No Known Activations