© 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. 8843
    Prev
    Next
    INDEX
    Explanations

    bulk

    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
    æµĩ
    -0.29
    esso
    -0.25
    æį®
    -0.25
     snap
    -0.25
    çIJĨçĶ±
    -0.25
    æĵļ
    -0.24
    forth
    -0.24
    \Log
    -0.23
    çļĦ责任
    -0.23
    åħ´
    -0.23
    POSITIVE LOGITS
    mates
    0.29
    ophilia
    0.26
    hana
    0.26
    lings
    0.25
    ivist
    0.25
    ewing
    0.25
    ]]></
    0.25
     silence
    0.24
     sak
    0.24
     arrivals
    0.24
    Activations Density 1.093%

    No Known Activations