© 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. 88025
    Prev
    Next
    INDEX
    Explanations

    agricultural

    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
     tow
    -0.25
    è¿ĩé«ĺ
    -0.24
     away
    -0.24
     trad
    -0.24
    criptors
    -0.23
    æ³Ĺ
    -0.23
    .Interop
    -0.23
     tradition
    -0.23
     pipes
    -0.23
    ahrain
    -0.23
    POSITIVE LOGITS
    æĻļ
    0.27
    ryn
    0.27
     upto
    0.25
     Olsen
    0.25
    -song
    0.25
    ons
    0.24
     inexp
    0.24
     Äijôi
    0.24
    èĦIJ
    0.24
    Ear
    0.24
    Activations Density 0.011%

    No Known Activations