© 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. 22-TRANSCODER-HP
    7. 87526
    Prev
    Next
    INDEX
    Explanations

    college

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     revisions
    -0.27
    -gallery
    -0.26
     cultivation
    -0.25
    warts
    -0.25
    arians
    -0.25
    ération
    -0.24
    ä¸Ģç»ı
    -0.24
    蹶
    -0.24
     professional
    -0.24
    çļĦä¸ĵä¸ļ
    -0.23
    POSITIVE LOGITS
    åIJ¦
    0.36
    ä¸Ģèĩ´æĢ§
    0.27
    RequiredMixin
    0.27
    idy
    0.25
    éļĪ
    0.25
    LOPT
    0.23
    Assistant
    0.23
    è§Į
    0.23
    onna
    0.23
    .mozilla
    0.23
    Activations Density 0.004%

    No Known Activations