© 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. 19800
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    缸
    -0.28
    venues
    -0.27
    è£ģ
    -0.26
    çĩ§
    -0.25
    hit
    -0.25
     getClient
    -0.25
    isk
    -0.24
    beck
    -0.23
     Beginner
    -0.23
    åµĺ
    -0.23
    POSITIVE LOGITS
    ampton
    0.30
    dorf
    0.27
    antine
    0.26
    æĨ©
    0.26
     kisses
    0.25
    GM
    0.25
    sst
    0.24
    onomous
    0.24
     pom
    0.24
    Concurrency
    0.24
    Activations Density 0.006%

    No Known Activations