© 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. 111911
    Prev
    Next
    INDEX
    Explanations

    after

    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
    illion
    -0.29
    ance
    -0.26
     awhile
    -0.26
    çĦī
    -0.25
    signal
    -0.25
    âĢ¦↵
    -0.24
    âĢ¦
    -0.24
    ä¸įå¿ħè¦ģçļĦ
    -0.23
    ãĤ«ãĥ³
    -0.23
    FORE
    -0.23
    POSITIVE LOGITS
    ableObject
    0.27
    è°¨
    0.26
    åİŁæľ¬
    0.25
     gegenüber
    0.25
    oku
    0.25
    ffset
    0.25
    æ±Łåİ¿
    0.25
    åĽłä¸ºå¥¹
    0.25
    ä¸į代表
    0.24
    pector
    0.24
    Activations Density 0.025%

    No Known Activations