© 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. 57493
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    ä¸Ńåħ±
    -0.30
     read
    -0.26
    读
    -0.25
    aland
    -0.25
     bur
    -0.25
     most
    -0.25
    heimer
    -0.25
    -read
    -0.24
     ’
    -0.24
    ]/
    -0.24
    POSITIVE LOGITS
     recognised
    0.28
     Guinness
    0.27
    .nl
    0.27
     specialised
    0.26
    Whilst
    0.25
    åĸĨ
    0.25
    åģĪ
    0.24
     choc
    0.24
    æĦŁå®ĺ
    0.24
     recognise
    0.24
    Activations Density 0.020%

    No Known Activations