© 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. 17951
    Prev
    Next
    INDEX
    Explanations

    stating a hypothesis

    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
    åģĩ
    -1.46
    åģĩ设
    -1.41
     suppose
    -1.30
     sup
    -1.29
    Sup
    -1.13
    sup
    -1.10
     Suppose
    -1.09
     assume
    -1.09
     Sup
    -1.07
     assumption
    -1.05
    POSITIVE LOGITS
    ((__
    0.30
    otten
    0.23
    ulp
    0.23
    lict
    0.22
    æķĿ
    0.22
    éª
    0.22
    èĩĬ
    0.22
    çıª
    0.22
     disin
    0.22
    £¼
    0.21
    Activations Density 0.958%

    No Known Activations