© 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. 24-TRANSCODER-HP
    7. 150735
    Prev
    Next
    INDEX
    Explanations

    software code and licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĸĩåĮĸ建设
    -0.27
    æ©Łæ§ĭ
    -0.26
    æ³ķå¾ĭ顾éĹ®
    -0.26
    bb
    -0.25
    år
    -0.25
    chia
    -0.25
    à¹Ģà¸Ī
    -0.24
    éĺ¿
    -0.24
    ased
    -0.24
    åĦ¿
    -0.24
    POSITIVE LOGITS
    -anchor
    0.27
    anmar
    0.27
     fl
    0.26
    @Web
    0.26
    .getHeader
    0.25
    .EventQueue
    0.25
    é³Į
    0.24
    imap
    0.24
    immer
    0.24
     focal
    0.23
    Activations Density 0.023%

    No Known Activations