© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161911
    Prev
    Next
    INDEX
    Explanations

    so

    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
    åIJĪæł¼
    -0.27
    è¿Ļæĺ¯ä¸Ģç§į
    -0.26
    éĩijåĪļ
    -0.25
     correct
    -0.25
    类似äºİ
    -0.25
     ÙħÙĪا
    -0.25
    è¾¹
    -0.25
    .key
    -0.24
    åį³åı¯
    -0.24
    æŃ£ç¡®çļĦ
    -0.24
    POSITIVE LOGITS
    ucer
    0.28
    agher
    0.27
     Coil
    0.25
    çĸ«æĥħå½±åĵį
    0.24
    Os
    0.24
     COUR
    0.24
    çļĦæīĭ
    0.24
    anker
    0.24
     PageInfo
    0.24
    AIT
    0.23
    Activations Density 0.002%

    No Known Activations