© 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. 98024
    Prev
    Next
    INDEX
    Explanations

    Connecting words

    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
    çļĦå°±æĺ¯
    -0.28
    utions
    -0.27
    ché
    -0.25
     miniature
    -0.25
    çľģ级
    -0.25
    elyn
    -0.24
    ably
    -0.24
    acie
    -0.24
    西
    -0.24
     sche
    -0.24
    POSITIVE LOGITS
    çŃīåĬŁèĥ½
    0.29
    iss
    0.27
    raphics
    0.26
    æİĸ
    0.24
     blows
    0.24
    æľīå¿ħè¦ģ
    0.24
    reme
    0.24
    -indent
    0.23
    è¾ľ
    0.23
     få
    0.23
    Activations Density 0.061%

    No Known Activations