© 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. 25-TRANSCODER-HP
    7. 107103
    Prev
    Next
    INDEX
    Explanations

    fracture

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ropri
    -0.27
     gard
    -0.26
     gr
    -0.26
    å¤ĸæı´
    -0.25
    åij
    -0.25
    è¸ı
    -0.25
    amped
    -0.25
    ¬ģ
    -0.24
     rings
    -0.24
    \$
    -0.24
    POSITIVE LOGITS
    abble
    0.27
    arts
    0.27
     culturally
    0.26
    pectrum
    0.26
    arus
    0.25
     occ
    0.25
    åıijå±ķéĺ¶æ®µ
    0.25
    _Construct
    0.25
    mitter
    0.24
    лез
    0.24
    Activations Density 1.342%

    No Known Activations