© 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. 87760
    Prev
    Next
    INDEX
    Explanations

    that

    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
    èĴŁ
    -0.28
    æIJŃä¹ĺ
    -0.27
    nces
    -0.27
     mortal
    -0.26
    lets
    -0.26
    å·ŀå¸Ĥ
    -0.25
    让人们
    -0.25
    æ·«
    -0.25
    巨人
    -0.24
    getting
    -0.24
    POSITIVE LOGITS
    å¿į
    0.28
    æľīæķĪ
    0.28
    oard
    0.28
    ä¸įåŃĺåľ¨
    0.26
    fern
    0.24
    nnen
    0.24
    nier
    0.24
    æĹº
    0.24
     DevExpress
    0.24
    åĬ¡å®ŀ
    0.24
    Activations Density 0.031%

    No Known Activations