© 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. 87346
    Prev
    Next
    INDEX
    Explanations

    social

    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
    istar
    -0.30
    ä¸Ńæłĩ
    -0.29
    .Params
    -0.26
    é¬Ĩ
    -0.26
    erts
    -0.26
    itti
    -0.25
    åīĮ
    -0.23
    ÐłÐĺ
    -0.23
    prise
    -0.23
    ikal
    -0.23
    POSITIVE LOGITS
    æ¾¹
    0.28
    饿
    0.27
    åĩĦ
    0.25
    Excel
    0.25
     resulting
    0.24
    çīĩåĮº
    0.24
    èĥĮ
    0.24
    æ·¡
    0.24
    ç§ijåѦéĻ¢
    0.24
    å°ıåĮº
    0.24
    Activations Density 0.039%

    No Known Activations