© 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. 4-TRANSCODER-HP
    7. 140
    Prev
    Next
    INDEX
    Explanations

    om

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atório
    -0.29
    èĭĭ
    -0.25
     Dell
    -0.25
    åĥļ
    -0.25
    даÑĩи
    -0.24
    ANEL
    -0.24
    frey
    -0.24
    riad
    -0.24
    idden
    -0.23
    adio
    -0.23
    POSITIVE LOGITS
    åĮħ
    0.27
    ä»ĸä¹Ł
    0.26
    ials
    0.25
    ëĦĪ
    0.25
     Barth
    0.25
    å·´
    0.24
    ç²Ĺ
    0.24
    ÑĩеÑģÑĤво
    0.24
    åĮ¹
    0.23
    æį£
    0.23
    Activations Density 3.049%

    No Known Activations