© 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. 18-TRANSCODER-HP
    7. 89457
    Prev
    Next
    INDEX
    Explanations

    Code/documentation/transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃĮ声
    -0.28
     oma
    -0.24
    æµĨ
    -0.24
    ÕŃ
    -0.24
     ov
    -0.23
    ä½Ĩä»ĸ们
    -0.23
    üz
    -0.23
     (.
    -0.23
     #__
    -0.23
    åħ¶ä¸Ń
    -0.23
    POSITIVE LOGITS
    ä¸ĩåħ¬éĩĮ
    0.28
    thesis
    0.28
    éĢĤåIJĪèĩªå·±
    0.27
    ä¸Ģ大åłĨ
    0.26
     hypert
    0.26
    asher
    0.26
     tempered
    0.25
    ames
    0.24
     magna
    0.24
    .ali
    0.24
    Activations Density 5.891%

    No Known Activations