© 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. 25-TRANSCODER-HP
    7. 108926
    Prev
    Next
    INDEX
    Explanations

    SQL, email, and webpages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¤ĸéĿ¢
    -0.28
    oins
    -0.27
    .retry
    -0.26
    åĪ©
    -0.26
    /screen
    -0.24
    çļĦæ¨¡æł·
    -0.24
     justify
    -0.24
    quez
    -0.23
    ä¸į大
    -0.23
    åĸ®
    -0.23
    POSITIVE LOGITS
    asive
    0.28
    æ¯Ĥ
    0.27
    åIJij社ä¼ļ
    0.26
    éĶ¦æłĩèµĽ
    0.26
    éķ¿
    0.26
    ç¡ķ士
    0.26
    å©¿
    0.25
    ál
    0.24
    æī¬
    0.24
     TBranch
    0.24
    Activations Density 0.026%

    No Known Activations