© 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. 42539
    Prev
    Next
    INDEX
    Explanations

    duration or extent

    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
     egret
    -0.23
    ç¿»è¯ij
    -0.23
    latent
    -0.23
     Ngb
    -0.23
     vscode
    -0.23
    æķ£
    -0.23
    YSTEM
    -0.23
    Phrase
    -0.23
    çĶŁäº§çļĦ
    -0.22
    解说
    -0.22
    POSITIVE LOGITS
    too
    0.33
     too
    0.33
    太ä¹ħ
    0.30
     an
    0.28
     Too
    0.28
     weakening
    0.28
    å¹´ä¹ĭä¹ħ
    0.27
    å¹´èµ·
    0.27
    -ahead
    0.27
    ilit
    0.26
    Activations Density 0.001%

    No Known Activations