© 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. 8288
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
    çijŀåħ¸
    -0.41
     Dutch
    -0.39
     Swedish
    -0.39
     Norway
    -0.37
     Norwegian
    -0.37
     Johan
    -0.35
     Nordic
    -0.35
    èĬ¬åħ°
    -0.34
     Netherlands
    -0.32
     Danish
    -0.32
    POSITIVE LOGITS
     additionally
    0.32
    baum
    0.29
    ataka
    0.27
    isches
    0.27
     prez
    0.27
    anz
    0.26
    é»ĦçŁ³
    0.26
    èģĶéĤ¦
    0.25
    æĻķ
    0.25
    èĪŁ
    0.25
    Activations Density 0.012%

    No Known Activations