© 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. 24678
    Prev
    Next
    INDEX
    Explanations

    Hungarian

    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
    è´¨éĩıå®īåħ¨
    -0.29
    ulaire
    -0.28
    tron
    -0.27
     Bain
    -0.26
    ragen
    -0.26
     posed
    -0.26
    vê
    -0.26
     mq
    -0.25
    дов
    -0.25
    rians
    -0.25
    POSITIVE LOGITS
    éĥ¨
    0.29
    横
    0.26
    .dir
    0.26
    å°ıæŶ
    0.26
    æ·ĺ
    0.26
    _hor
    0.26
     hor
    0.26
    æłı
    0.26
    åĬŀ
    0.26
     Ãľ
    0.26
    Activations Density 0.093%

    No Known Activations