© 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. 30-TRANSCODER-HP
    7. 97160
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ruk
    -0.31
    .removeFrom
    -0.30
    å¹²
    -0.26
    æ¶Ī失
    -0.25
    mad
    -0.25
    ifty
    -0.25
    rons
    -0.25
    etri
    -0.25
    apot
    -0.24
    ugi
    -0.24
    POSITIVE LOGITS
    å±Ģ
    0.29
    å£ķ
    0.26
     púb
    0.26
     lasting
    0.26
    ITIVE
    0.25
    æĹ¥èµ·
    0.25
    ATIVE
    0.25
     insensitive
    0.25
    ção
    0.25
    æľªç»ı
    0.25
    Activations Density 0.883%

    No Known Activations

    This feature has no known activations.