© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18934
    Prev
    Next
    INDEX
    Explanations

    articles (a, an, the)

    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
    Not in Any Lists

    No Comments

    Negative Logits
    缴åĪ°
    -0.28
    imony
    -0.28
    æŁ¯
    -0.27
    melon
    -0.27
    hk
    -0.26
    StatusLabel
    -0.26
    åħ«åįģ
    -0.25
    ç½ijé¦ĸ页
    -0.25
    æIJ¬åĪ°
    -0.25
    Ordinal
    -0.25
    POSITIVE LOGITS
     collection
    0.30
    çĽ¾
    0.28
     fundamental
    0.28
     single
    0.27
     gate
    0.27
     Signals
    0.27
     breathing
    0.26
    -link
    0.26
    ç¼ļ
    0.26
     pool
    0.25
    Activations Density 0.988%

    No Known Activations