© 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. 27-TRANSCODER-HP
    7. 9054
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĵ好
    -0.31
    åħģ许
    -0.28
    ront
    -0.26
     tolerance
    -0.25
     allowance
    -0.25
     tolerant
    -0.25
    åĩĨ
    -0.24
     witnessing
    -0.24
    å°Ĭ
    -0.24
     Bund
    -0.24
    POSITIVE LOGITS
    æīĵæĸŃ
    0.29
    忽çĦ¶
    0.28
    æĶ¹åıĺ
    0.28
    åįķ
    0.27
    vae
    0.26
    ANCEL
    0.26
    å¨ģå°Ķ
    0.26
     disconnect
    0.26
    ppe
    0.25
    åĨ»ç»ĵ
    0.25
    Activations Density 0.008%

    No Known Activations