© 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. 31-TRANSCODER-HP
    7. 18710
    Prev
    Next
    INDEX
    Explanations

    Formal writing or coding text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Acquisition
    -0.29
    ari
    -0.26
     Ele
    -0.25
     acquisition
    -0.25
    naires
    -0.25
    eed
    -0.25
    祲
    -0.24
    [value
    -0.24
    Execution
    -0.24
     acquisitions
    -0.24
    POSITIVE LOGITS
    anel
    0.26
    anus
    0.26
    è°ģèĥ½
    0.25
    -tax
    0.25
    à¹ģà¸ĭ
    0.25
    apped
    0.25
    Äĥng
    0.25
    éŀŃ
    0.25
     pellets
    0.25
    tan
    0.25
    Activations Density 0.129%

    No Known Activations