© 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. 23-TRANSCODER-HP
    7. 25543
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åıªæľīä¸Ģ个
    -0.28
     ones
    -0.28
     only
    -0.27
     section
    -0.27
    edio
    -0.26
    bots
    -0.25
    .Bot
    -0.24
     solely
    -0.24
    pte
    -0.24
    åķ¼
    -0.24
    POSITIVE LOGITS
    天çĦ¶
    0.27
    å±ħ
    0.26
     muster
    0.26
    onor
    0.25
    èĩ³æĸ¼
    0.25
     Keeps
    0.25
    iosa
    0.24
    ä¸Ģæŀļ
    0.24
    erti
    0.24
    isse
    0.24
    Activations Density 0.006%

    No Known Activations