© 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. 22-TRANSCODER-HP
    7. 87624
    Prev
    Next
    INDEX
    Explanations

    Start of sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auen
    -0.28
    stown
    -0.26
     verso
    -0.26
    apa
    -0.25
    ÃŃcio
    -0.24
     rac
    -0.24
    oller
    -0.24
     Behavioral
    -0.24
    Att
    -0.23
     unnamed
    -0.23
    POSITIVE LOGITS
     sodom
    0.27
    æĸIJ
    0.24
    çĹĩ
    0.23
    æĺ¯ä¸Ģ款
    0.23
     stockings
    0.23
     bottoms
    0.23
    å·¥ç¨ĭæľºæ¢°
    0.23
    нÑıÑĤи
    0.22
    bag
    0.22
     yoÄŁun
    0.22
    Activations Density 0.005%

    No Known Activations