© 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. 24389
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
    硬åĮĸ
    -0.27
    æŀķ
    -0.26
    оÑĢа
    -0.26
    ogn
    -0.26
    åĽłä¸ºæĪij们
    -0.26
    éĺ¿æł¹
    -0.25
    æĴ¥
    -0.24
    FormsModule
    -0.24
    æĭ¨
    -0.24
    æ¡ĥ
    -0.24
    POSITIVE LOGITS
    享åıĹ
    0.29
     atoi
    0.29
    rah
    0.29
    享
    0.27
    èĩªæĿĢ
    0.27
    åĨķ
    0.26
    antics
    0.25
     Vacation
    0.25
    acie
    0.25
    ä»·åĢ¼
    0.25
    Activations Density 0.014%

    No Known Activations