© 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. 88953
    Prev
    Next
    INDEX
    Explanations

    Legal case documents

    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
    FRING
    -0.26
    SCRIBE
    -0.25
    饲
    -0.25
    č↵č↵
    -0.25
     exercÃŃcio
    -0.24
     tilted
    -0.24
    èĢĥ
    -0.24
    acies
    -0.23
    obil
    -0.23
     Paths
    -0.23
    POSITIVE LOGITS
    åľ¨å¹¿å·ŀ
    0.26
    locales
    0.26
    anggan
    0.24
    è¯įæĿ¡
    0.24
    rapper
    0.24
    whereIn
    0.23
    åıĺäºĨ
    0.23
    illian
    0.23
    izzard
    0.23
    ake
    0.23
    Activations Density 0.002%

    No Known Activations