© 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. 149850
    Prev
    Next
    INDEX
    Explanations

    applications in various fields

    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
     Inn
    -0.26
    åĨħéĥ¨
    -0.25
    etrain
    -0.25
    浩
    -0.24
    å®ŀè´¨æĢ§
    -0.24
    æľ¬åľ°
    -0.23
    Internal
    -0.23
    inerary
    -0.23
    æķ´è½¦
    -0.23
    .digest
    -0.23
    POSITIVE LOGITS
    è¯ģåĪ¸æĬķèµĦ
    0.28
    ä¼¼çļĦ
    0.26
    ä¸IJ
    0.25
     ..."↵↵
    0.24
    ãĦŁ
    0.24
    udo
    0.24
    izes
    0.23
    çĽ²
    0.23
    诤
    0.23
    udies
    0.23
    Activations Density 0.135%

    No Known Activations