© 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. 24-TRANSCODER-HP
    7. 151327
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å½Ĵ
    -0.27
    å½Ĵå±ŀ
    -0.26
     insights
    -0.26
    ķìĿ¸
    -0.26
    è¯ģæĺİ
    -0.25
    ä¸įä»ħå¦ĤæѤ
    -0.24
    ãģĵãĤį
    -0.23
    hänge
    -0.23
     hints
    -0.23
    abilia
    -0.23
    POSITIVE LOGITS
    anas
    0.29
    ailing
    0.26
    ä¸Ģ个å¤ļ
    0.26
    åħ³çĪ±
    0.25
    enis
    0.25
    strt
    0.24
    ande
    0.24
     pan
    0.24
    cef
    0.24
     panicked
    0.24
    Activations Density 0.157%

    No Known Activations