© 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. 8420
    Prev
    Next
    INDEX
    Explanations

    introductions

    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
    åĪĩæį¢
    -0.29
    aña
    -0.27
     mar
    -0.24
    å¢Ļ
    -0.24
    å¬ī
    -0.24
     UIT
    -0.24
    vol
    -0.24
     tuned
    -0.23
     cup
    -0.23
     recommendation
    -0.23
    POSITIVE LOGITS
     how
    0.33
     why
    0.30
    为ä»Ģä¹Ī
    0.30
     How
    0.29
    å¦Ĥä½ķ
    0.28
    æĢİ
    0.28
     what
    0.28
     поÑĩемÑĥ
    0.27
    isor
    0.27
     cómo
    0.27
    Activations Density 0.000%

    No Known Activations