© 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. 130374
    Prev
    Next
    INDEX
    Explanations

    blog posts

    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
    åĽŀåIJĪ
    -0.37
    å®ĺ
    -0.32
    åĽŀ
    -0.28
    ä»ĸ说
    -0.26
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.26
    xies
    -0.24
    å¹³
    -0.24
    éŀħ
    -0.24
    è®®
    -0.24
    æĴij
    -0.24
    POSITIVE LOGITS
    让人
    0.28
    iaux
    0.28
     festive
    0.28
    -family
    0.28
    ROID
    0.27
    discover
    0.26
    让çĶ¨æĪ·
    0.26
    è®ĵ人
    0.26
    family
    0.26
     QLD
    0.26
    Activations Density 0.063%

    No Known Activations