© 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. 131243
    Prev
    Next
    INDEX
    Explanations

    are/were/be

    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
     ihnen
    -0.28
     them
    -0.27
    ä¸Ģ项
    -0.27
    渥
    -0.26
     ниÑħ
    -0.26
    WWW
    -0.25
    ez
    -0.25
     Difficulty
    -0.25
     They
    -0.24
    They
    -0.24
    POSITIVE LOGITS
     functionalities
    0.31
    inox
    0.27
    umba
    0.27
     púb
    0.26
    éĤ£äºĽ
    0.24
    éĻĦåĬłåĢ¼
    0.24
    those
    0.24
    缸ç»ĵåIJĪ
    0.24
     analyses
    0.23
    è¿ĽäºĨ
    0.23
    Activations Density 0.016%

    No Known Activations