© 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. 24226
    Prev
    Next
    INDEX
    Explanations

    memory

    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
     memor
    -0.26
    æŀ¢
    -0.25
     fre
    -0.25
    peg
    -0.24
    åĬĽ
    -0.24
     bour
    -0.24
    systems
    -0.24
     knows
    -0.24
     hyper
    -0.23
    urers
    -0.23
    POSITIVE LOGITS
    clus
    0.30
    åĻ«
    0.29
    trak
    0.28
    cov
    0.27
    æݥ触
    0.26
    TypeInfo
    0.26
    æ¯ĽåŃĶ
    0.26
    大æłij
    0.25
     Gallup
    0.24
    æķ£
    0.24
    Activations Density 0.038%

    No Known Activations