© 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. 30-TRANSCODER-HP
    7. 95502
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ev
    -0.29
     single
    -0.27
    InstanceId
    -0.26
    single
    -0.26
     SINGLE
    -0.26
    åĽ½ç«ĭ
    -0.26
    åį°
    -0.26
     Single
    -0.26
     Hollow
    -0.26
    èģ¯
    -0.26
    POSITIVE LOGITS
    举æĸ¹
    0.26
    xD
    0.26
    unks
    0.26
    imid
    0.26
     Britann
    0.25
    æ½Ł
    0.24
     Hispan
    0.24
    ext
    0.24
    å±±åİ¿
    0.24
    Containing
    0.24
    Activations Density 0.977%

    No Known Activations