© 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. 23-TRANSCODER-HP
    7. 25025
    Prev
    Next
    INDEX
    Explanations

    saving/marking for later

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elage
    -0.29
    è¿ĺä¼ļ
    -0.27
    olation
    -0.27
    éĹ´éļĶ
    -0.25
    æīįä¼ļ
    -0.25
    лÑİ
    -0.25
    ampus
    -0.24
    quests
    -0.24
    agr
    -0.23
    amba
    -0.23
    POSITIVE LOGITS
    çļĦåį°è±¡
    0.27
     liberation
    0.26
    romium
    0.26
     table
    0.26
    çķĮçļĦ
    0.25
    _table
    0.25
    解æĶ¾
    0.24
    æī¼
    0.24
    æĥľ
    0.24
     Table
    0.24
    Activations Density 0.007%

    No Known Activations