© 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. 22425
    Prev
    Next
    INDEX
    Explanations

    Monitoring changes

    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
    orgh
    -0.32
    ona
    -0.26
     divis
    -0.26
    åħľ
    -0.25
    orce
    -0.25
    енд
    -0.25
     indem
    -0.24
    衽
    -0.24
    mite
    -0.24
     coup
    -0.24
    POSITIVE LOGITS
    åıĺåĮĸ
    0.31
    çļĦåıĺåĮĸ
    0.28
    åıijçĶŁåıĺåĮĸ
    0.26
     expressive
    0.25
    WithTag
    0.25
     gone
    0.25
    baseline
    0.25
    对æ¯Ķ
    0.25
    çħĮ
    0.24
     contrast
    0.24
    Activations Density 0.003%

    No Known Activations