© 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. 32-TRANSCODER-HP
    7. 43585
    Prev
    Next
    INDEX
    Explanations

    scientific articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡Ģ
    -0.28
    tri
    -0.28
     اÙĦصÙģ
    -0.28
    ↵                    ↵
    -0.26
    timeofday
    -0.26
     hÃłi
    -0.25
    çµ®
    -0.25
    ·»
    -0.25
    Tri
    -0.25
    é£ŀæľº
    -0.25
    POSITIVE LOGITS
     ferment
    0.30
     erupted
    0.27
    OLON
    0.27
    lazy
    0.26
    apor
    0.26
     lazy
    0.25
    acco
    0.25
     oxid
    0.25
    æĺ¥èĬĤæľŁéĹ´
    0.24
     laz
    0.24
    Activations Density 0.001%

    No Known Activations