© 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. 98098
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Anth
    -0.28
    tra
    -0.26
    ste
    -0.26
    omorphic
    -0.26
     human
    -0.25
    .multipart
    -0.25
     part
    -0.25
    èį·
    -0.24
     parte
    -0.24
     laure
    -0.24
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.32
    esome
    0.26
    ï¼
    0.25
    ordination
    0.25
    WSC
    0.25
     UNITY
    0.25
    å¼łæī¬
    0.24
    å¾Īé«ĺçļĦ
    0.24
    éĴª
    0.24
    влек
    0.24
    Activations Density 0.009%

    No Known Activations