© 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. 31-TRANSCODER-HP
    7. 19777
    Prev
    Next
    INDEX
    Explanations

    variations of word settle

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    £¼
    -0.28
    éĢµ
    -0.27
     bert
    -0.25
    ritch
    -0.25
    аÑģÑĤ
    -0.24
    егиÑģÑĤ
    -0.24
    ayah
    -0.24
    樯
    -0.24
    .rc
    -0.23
    oldt
    -0.23
    POSITIVE LOGITS
     settle
    1.32
     settling
    1.23
     settled
    1.19
     settles
    1.15
     settlement
    1.00
     Settlement
    0.87
     settlements
    0.84
    sett
    0.84
    ç»ĵç®Ĺ
    0.63
    å®ļå±ħ
    0.60
    Activations Density 34.335%

    No Known Activations