© 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. 22-TRANSCODER-HP
    7. 131010
    Prev
    Next
    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Merc
    -0.27
    å¹´ãģ«
    -0.27
    OrFail
    -0.26
    ä¹°åĪ°
    -0.25
    è´§
    -0.25
    ære
    -0.25
     ECC
    -0.25
    éĢł
    -0.25
    avit
    -0.25
     flex
    -0.24
    POSITIVE LOGITS
     openness
    0.35
    åħ¬å¼Ģ
    0.32
     setHidden
    0.30
    ople
    0.30
    Uploaded
    0.29
     tours
    0.29
    UBLIC
    0.28
    ready
    0.28
     leaks
    0.28
     expose
    0.28
    Activations Density 0.015%

    No Known Activations