© 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. 19554
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     mut
    -0.30
    æĿĥ
    -0.29
     thorough
    -0.29
     magnet
    -0.28
    饮
    -0.28
    å®ļå¾ĭ
    -0.27
    æĬĵä½ı
    -0.27
    ettes
    -0.27
     viene
    -0.27
    欲
    -0.25
    POSITIVE LOGITS
    åŁºç¡Ģ
    0.36
    åŁºç¤İ
    0.30
    èĤ¤èī²
    0.28
     Decompiled
    0.27
    apro
    0.27
    ä¹ĭ家
    0.26
    åŁºçŁ³
    0.26
    estr
    0.26
    ãĥķãĥ©
    0.26
     Cheat
    0.25
    Activations Density 0.007%

    No Known Activations