© 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. 31-TRANSCODER-HP
    7. 19772
    Prev
    Next
    INDEX
    Explanations

    case

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Wich
    -0.27
    èĴĻ
    -0.27
    æŁľ
    -0.27
    eteria
    -0.26
     mont
    -0.26
     bè
    -0.25
    æį
    -0.25
     csr
    -0.25
    concat
    -0.25
     shr
    -0.24
    POSITIVE LOGITS
     case
    0.35
    Case
    0.33
    _case
    0.32
     cases
    0.31
    -case
    0.30
    case
    0.30
    åīĤ
    0.29
     SO
    0.28
     Case
    0.28
    AG
    0.27
    Activations Density 0.998%

    No Known Activations