© 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. 149277
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    gone
    -0.28
    çŀij
    -0.27
    åŁºè¾ħ
    -0.26
    thrown
    -0.26
    å½ĵæĪij
    -0.26
    ĪæĿĥ
    -0.24
     initialised
    -0.24
     discarded
    -0.24
     contained
    -0.24
     bene
    -0.24
    POSITIVE LOGITS
    achu
    0.25
    çłĶ究
    0.25
     ÑģÑĤÑĥд
    0.24
     candidate
    0.24
    DMI
    0.24
     Há»ĵ
    0.24
    èģĮä¸ļçĶŁæ¶¯
    0.24
    .gs
    0.24
    bach
    0.23
    ced
    0.23
    Activations Density 0.944%

    No Known Activations